What is the right geometry for enabling principled steering of neural network behavior?

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Manifold steering for neural network controlconcept0.799
• Neural representation geometry causally shapes behavior; interventions respecting that geometry will yield natural trajectories.hypothesis0.799
  Central hypothesis tested via manifold steering experiments across language models and video world models.
• Manifold steering demonstrates bidirectional geometry-behavior link in a video world model on tasks with geometry corresponding to physical dynamicsfinding0.784
  Extension of manifold steering validation to video world models and physical dynamics tasks, demonstrating cross-modal generality
• Geometry in neural representation is not merely incidental, but is in fact the proper object for enabling principled control via intervention on internals.claim0.783
  Core interpretive assertion: geometric structure is causally load-bearing, not epiphenomenal.
• There exists a bidirectional relationship between the geometry of neural representation and the geometry of model behaviorclaim0.779
  Central empirical claim of the paper, demonstrated across tasks and modalities
• There is a clear bidirectional relationship between the geometry of behavior and representation: steering along representation manifolds follows behavior manifolds, and vice versa.claim0.776
  The paper's finding that the alignment holds in both directions — from representation to behavior and from behavior back to representation space.
• neural behavior geometryconcept0.776
  The manifold structure of model outputs, modelled by M_y.
• Manifold-respecting steering produces smooth natural behavioral trajectories while linear steering teleports between non-adjacent concepts.claim0.774