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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oints
    -0.08
    tik
    -0.08
    脸
    -0.08
     jug
    -0.08
     depicting
    -0.08
     ayaa
    -0.07
     deducted
    -0.07
    stal
    -0.07
    astus
    -0.07
    acket
    -0.07
    POSITIVE LOGITS
    bei
    0.07
     ус
    0.07
     Erm
    0.07
     reputable
    0.07
    га
    0.07
    0.07
    ती
    0.07
     grocery
    0.07
     datas
    0.07
     Cardi
    0.07
    Act Density 0.017%
    No Known Activations