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

    Neuronpedia

    INDEX
    Explanations

    programming errors

    np_max-act · gemini-2.0-flash

    The neuron fires on compiler error messages complaining about undeclared or unresolved identifiers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _InternalArray
    -0.08
    至少
    -0.06
     snapshots
    -0.06
    titleLabel
    -0.06
    исс
    -0.06
    留
    -0.06
     COMP
    -0.06
    _FILL
    -0.06
    (time
    -0.06
     зад
    -0.06
    POSITIVE LOGITS
     품
    0.07
     **)
    0.07
    .Paint
    0.07
    /Runtime
    0.06
    oi
    0.06
    ,status
    0.06
    'in
    0.06
     khá
    0.06
     Determines
    0.06
     Upon
    0.06
    Act Density 0.024%

    No Known Activations