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

    Neuronpedia

    INDEX
    Explanations

    Troubled lives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Resource
    -0.06
     esto
    -0.06
    ivě
    -0.06
    QUE
    -0.06
     getP
    -0.06
     Kürt
    -0.06
     uphill
    -0.06
     gears
    -0.06
     pw
    -0.06
    ือถ
    -0.06
    POSITIVE LOGITS
     Chiefs
    0.07
     seiz
    0.06
    ongo
    0.06
    aepernick
    0.06
     догов
    0.06
    resents
    0.06
     conhe
    0.06
    rieg
    0.06
    .each
    0.06
     Introduced
    0.06
    Act Density 0.210%

    No Known Activations