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

    Neuronpedia

    INDEX
    Explanations

    Dialogue

    np_max-act · gemini-2.0-flash

    This neuron never activates—it does not respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Mode
    -0.07
     maz
    -0.07
    _Draw
    -0.07
    Upper
    -0.07
     Pierce
    -0.07
     kok
    -0.06
    Fold
    -0.06
     Gauge
    -0.06
     E
    -0.06
     Mount
    -0.06
    POSITIVE LOGITS
     інозем
    0.06
     管
    0.06
    жи
    0.06
    ',...↵
    0.06
     अपन
    0.06
    .aggregate
    0.06
     $($
    0.06
    .student
    0.06
    tries
    0.06
    (food
    0.06
    Act Density 0.037%

    No Known Activations