To be honest, I don’t know! What’s the criteria for “extreme voting” on either side? On the other hand, what’s the criteria for “moderate voting” on either side?
https://www.govtrack.us/about/analysis#ideology
They talk about how this doesn't actually track ideology in an abstract sense: It actually tracks how often members write bills with their political bloc.
"Moderate" voting under this methodology is: Does the member cross the aisle to craft or promote legislation.
"In a nutshell, Members of Congress who cosponsor similar sets of bills will get scores close together, while Members of Congress who sponsor different sets of bills will have scores far apart. Members of Congress with similar political views will tend to cosponsor the same set of bills, or bills by the same set of authors, and inversely Members of Congress with different political views will tend to cosponsor different bills."
The outliers are people that only work with their own party ... or rarely with others -- technically the bounds are undefined; the people on the extremes could have worked dozens of times with members of the opposite party but the people in the middle might have done so thousands of times and it would produce the same result. The scale of the axes in the chart is unlabeled.
There is also a subtle problem in that people who introduce fewer bills will tend toward the center faster even when working across the aisle less. Someone near the top left (/right) corner can have collaborated an
equal number of times as someone in the bottom right (/left) but they will weight away from the center simply by working
more often with their own party. This doesn't actually say anything about their willingness to work across the aisle: It could indicate few opportunities, a newer member of congress, fewer members of their own party in congress (although I think the timeline of the chart does result in a relatively even split), less interest in (co-)sponsoring bills (not everyone in congress is cut out for that job), less interest in working with other members of congress regardless of party -- that's just off the top of my head thinking for as long as this took to type. I'm sure everyone could come up with other reasons.
The underlying data is probably useful for something, but the chart itself isn't a fantastic presentation and it's
demonstrably prone to wild misinterpretation, even according to its authors.