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

    Neuronpedia

    INDEX
    Explanations

    Literature extracts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yo
    -0.07
    .Com
    -0.07
    hone
    -0.07
     Shopify
    -0.07
    ,module
    -0.06
     demon
    -0.06
    _GPIO
    -0.06
     tome
    -0.06
    (sock
    -0.06
     kf
    -0.06
    POSITIVE LOGITS
    越好
    0.07
     Athletic
    0.07
    财运
    0.07
     Creed
    0.06
    周边
    0.06
    平方米
    0.06
    势头
    0.06
    يز
    0.06
    感じ
    0.06
    /job
    0.06
    Act Density 0.005%

    No Known Activations