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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash

    The neuron flags numeric expressions of ages and time intervals (e.g. “age at,” “mean time,” “months,” “years”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gardner
    -0.07
     batt
    -0.06
    Output
    -0.06
    DATA
    -0.06
    oup
    -0.06
     CO
    -0.06
     Gef
    -0.06
     bubble
    -0.06
    _metric
    -0.06
     charitable
    -0.06
    POSITIVE LOGITS
    (always
    0.08
    ')
↵
    0.06
    icipant
    0.06
    장을
    0.06
    σμο
    0.06
    chs
    0.06
     ürün
    0.06
    zyst
    0.06
     serializer
    0.06
    voucher
    0.06
    Act Density 0.006%

    No Known Activations