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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     문의
    -0.07
    .tokens
    -0.07
    _Number
    -0.06
     документ
    -0.06
    dül
    -0.06
    ules
    -0.06
    вол
    -0.06
     센
    -0.06
     dưỡng
    -0.06
    _ff
    -0.06
    POSITIVE LOGITS
    (QStringLiteral
    0.07
     ~/.
    0.07
    езульт
    0.07
    -б
    0.07
     прямо
    0.07
     pharmacist
    0.06
    :')
    0.06
     '');↵↵
    0.06
    -project
    0.06
    μέ
    0.06
    Act Density 0.019%

    No Known Activations