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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ex
    -0.07
     show
    -0.06
     challenging
    -0.06
    ранения
    -0.06
     kid
    -0.06
    olian
    -0.06
     courageous
    -0.06
    旧
    -0.06
     กรกฎาคม
    -0.06
     constitutional
    -0.06
    POSITIVE LOGITS
     basePath
    0.07
    もり
    0.07
     *[
    0.06
    Enough
    0.06
    .TRAN
    0.06
    /conf
    0.06
    	W
    0.06
     詳細
    0.06
     separates
    0.06
    \param
    0.06
    Act Density 0.090%

    No Known Activations