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

    Neuronpedia

    INDEX
    Explanations

    mathematical assignments

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—especially decimal number substrings—indicating it detects numeric literals (e.g. fractional or floating-point values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fist
    -0.07
    _identity
    -0.06
    getDrawable
    -0.06
    _EXPORT
    -0.06
    Properties
    -0.06
    Security
    -0.06
    _DT
    -0.06
    Entry
    -0.06
    ocrats
    -0.06
     Duty
    -0.06
    POSITIVE LOGITS
    expire
    0.06
     nebylo
    0.06
     formatDate
    0.06
     ไ
    0.06
     sims
    0.06
    .Uint
    0.06
     πο
    0.06
     még
    0.06
    สาร
    0.06
     hace
    0.06
    Act Density 0.006%

    No Known Activations