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

    Neuronpedia

    INDEX
    Explanations

    news reports

    np_max-act · gemini-2.0-flash

    This neuron activates on numbers and numerical details (e.g. figures, measurements, dates, quantities).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gary
    -0.08
     IPP
    -0.07
     Casa
    -0.07
     Gür
    -0.07
     Rah
    -0.06
     객체
    -0.06
     subplot
    -0.06
     knitting
    -0.06
     Pool
    -0.06
     EXPRESS
    -0.06
    POSITIVE LOGITS
    بو
    0.07
    _en
    0.07
    فران
    0.06
     begun
    0.06
    IMIZE
    0.06
    .month
    0.06
    念
    0.06
    interested
    0.06
    .android
    0.06
    _changed
    0.06
    Act Density 0.275%

    No Known Activations