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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ública
    -0.07
    failure
    -0.07
     tract
    -0.07
    udoku
    -0.07
    cht
    -0.07
    _Api
    -0.06
     green
    -0.06
     انجام
    -0.06
     stars
    -0.06
     reader
    -0.06
    POSITIVE LOGITS
    ливо
    0.07
    .Quad
    0.06
    wchar
    0.06
    -wise
    0.06
    ={<
    0.06
     Cannot
    0.06
    нолог
    0.06
    菲
    0.06
     міжнарод
    0.06
     законодав
    0.06
    Act Density 0.004%

    No Known Activations