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

    Neuronpedia

    INDEX
    Explanations

    measurements

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric measurement tokens (e.g. dimensions, heights, floor‐to‐floor values, square footage).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tuyến
    -0.07
    �에
    -0.06
     buffalo
    -0.06
     eing
    -0.06
    }-${
    -0.06
     amore
    -0.06
     الدولي
    -0.06
    -за
    -0.06
    وغ
    -0.06
     IMapper
    -0.06
    POSITIVE LOGITS
     delayed
    0.07
     setId
    0.07
    <Element
    0.07
    /terms
    0.06
     Breast
    0.06
    (sql
    0.06
     literature
    0.06
     [*
    0.06
     income
    0.06
    -art
    0.06
    Act Density 0.009%

    No Known Activations