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

    Neuronpedia

    INDEX
    Explanations

    math statistics

    np_max-act · gemini-2.0-flash

    This neuron lights up on mathematical/statistical notation—especially numeric expressions, decimal numbers, and formula‐style tokens like “i.i.d.”.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    aking
    -0.07
    Duplicates
    -0.06
    -ended
    -0.06
     BUS
    -0.06
    living
    -0.06
     степени
    -0.06
    老
    -0.06
    groupBox
    -0.06
     vět
    -0.06
    ์ล
    -0.06
    POSITIVE LOGITS
     snapshot
    0.08
     μέχρι
    0.07
    (import
    0.07
    Cİ
    0.07
    invite
    0.07
     =$
    0.07
    :The
    0.07
    ??
    0.06
    ??
    0.06
    astically
    0.06
    Act Density 0.005%

    No Known Activations