Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior

ArXi:2605.05115v1 Announce Type: new Neural representations carry rich geometric structure; but does that structure causally shape behavior? To address this question, we intervene along paths through activation space defined by different geometries, and measure the behavioral trajectories they induce. In particular, we test whether interventions that respect the geometry of activation space will yield behaviors close to those the model exhibits naturally.