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

    Neuronpedia

    INDEX
    Explanations

    code style naming conventions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    154
    -0.07
    (cell
    -0.07
    оть
    -0.07
    bek
    -0.07
    уд
    -0.06
    对于
    -0.06
     nose
    -0.06
     Lim
    -0.06
     uw
    -0.06
     getColumn
    -0.06
    POSITIVE LOGITS
     healthy
    0.07
    .abstract
    0.07
    ＿＿＿＿＿＿＿＿
    0.06
    .El
    0.06
     nghị
    0.06
     Annotations
    0.06
     rug
    0.06
     flowed
    0.06
     İngilizce
    0.06
     só
    0.06
    Act Density 0.190%

    No Known Activations