neural behavior geometry

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

• Neural Geometry Frameworkframework0.860
  Conceptual scheme introduced in this paper: neural networks develop internal geometric representations that mirror real-world geometry, providing the right level of description for interpretability and control.
• Neural Geometriesconcept0.850
• Neural representation geometry causally shapes behavior; interventions respecting that geometry will yield natural trajectories.hypothesis0.813
  Central hypothesis tested via manifold steering experiments across language models and video world models.
• There exists a bidirectional relationship between the geometry of neural representation and the geometry of model behaviorclaim0.786
  Central empirical claim of the paper, demonstrated across tasks and modalities
• neural cognitionconcept0.780
  Cognition in nervous systems, used as a modelling target
• What is the right geometry for enabling principled steering of neural network behavior?question0.776
  The reframed steering problem the paper introduces
• Geometry unifies diverse neural architectures in machine learning systems.claim0.775
• Neural Annealingframework0.768
  Michael Johnson's prior work on how neural networks (and brains) can be 'annealed' to find optimal states.