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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron detects numeric literals, especially floating‐point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     flair
    -0.07
    oters
    -0.06
     Applies
    -0.06
     tavs
    -0.06
    /stream
    -0.06
    _begin
    -0.06
    _stat
    -0.06
     بغ
    -0.06
     busca
    -0.06
     rad
    -0.06
    POSITIVE LOGITS
     อำเภ
    0.07
    createFrom
    0.06
    ाद
    0.06
    REF
    0.06
     Machine
    0.06
    Bill
    0.06
     Res
    0.06
    성이
    0.06
     Welfare
    0.06
    亚洲
    0.06
    Act Density 0.426%

    No Known Activations