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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     решил
    -0.08
     specimens
    -0.07
    Detail
    -0.07
    規定
    -0.07
    (decoded
    -0.07
     Как
    -0.07
     calories
    -0.07
    Виде
    -0.06
     Corey
    -0.06
    gráfico
    -0.06
    POSITIVE LOGITS
    /table
    0.07
    反映了
    0.07
     następ
    0.06
    裣
    0.06
    amework
    0.06
    对抗
    0.06
    智造
    0.06
    伴
    0.06
     סביב
    0.06
     unaffected
    0.06
    Act Density 0.066%

    No Known Activations