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

    Neuronpedia

    INDEX
    Explanations

    conversational replies

    np_max-act · gemini-2.0-flash

    The neuron detects floating‐point numeric literals (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    タル
    -0.07
    ックス
    -0.07
    ãi
    -0.07
    niejs
    -0.07
    etal
    -0.06
     ancora
    -0.06
    StringUtil
    -0.06
     Fern
    -0.06
     peč
    -0.06
     significance
    -0.06
    POSITIVE LOGITS
     результате
    0.06
    _null
    0.06
     zie
    0.06
     дв
    0.06
     مص
    0.06
     اثر
    0.06
     equivalent
    0.06
    someone
    0.06
    .setContentType
    0.06
     cellpadding
    0.06
    Act Density 0.023%

    No Known Activations