Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    model class

    np_max-act · gemini-2.0-flash

    This neuron responds to code‐related identifiers, especially references to “Model” (and related terms like models.py, class, .Model) in programming snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ambil
    -0.07
    Names
    -0.07
    Standing
    -0.07
    川
    -0.06
     Chevron
    -0.06
    Saved
    -0.06
    OFFSET
    -0.06
    anticipated
    -0.06
     peş
    -0.06
     matte
    -0.06
    POSITIVE LOGITS
    ffi
    0.08
     Reception
    0.08
     acl
    0.08
     corporations
    0.08
     corporation
    0.07
    �
    0.07
    HandlerContext
    0.07
    )에
    0.07
    .Destroy
    0.07
     implemented
    0.06
    Act Density 0.023%

    No Known Activations