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

    Neuronpedia

    INDEX
    Explanations

    software upgrading

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contemplated
    -0.07
    مام
    -0.07
    agrid
    -0.06
    erglass
    -0.06
     personalized
    -0.06
     katılım
    -0.06
    entine
    -0.06
    क
    -0.06
     Continuous
    -0.06
     etmiştir
    -0.06
    POSITIVE LOGITS
    _UN
    0.07
    (QStringLiteral
    0.07
     Incorpor
    0.06
     darken
    0.06
    ści
    0.06
    trees
    0.06
     tyto
    0.06
     İs
    0.06
    ď
    0.06
     offs
    0.06
    Act Density 0.085%

    No Known Activations