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

    Neuronpedia

    INDEX
    Explanations

    punctuation/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    why
    -0.07
    defense
    -0.06
     converting
    -0.06
    ektiv
    -0.06
     onPostExecute
    -0.06
     Jew
    -0.06
    _Input
    -0.06
    834
    -0.06
    atomy
    -0.06
     ey
    -0.06
    POSITIVE LOGITS
    マン
    0.07
     konut
    0.07
     parallel
    0.07
    تان
    0.07
     літ
    0.06
     Пра
    0.06
     stati
    0.06
    uner
    0.06
    parallel
    0.06
    ��
    0.06
    Act Density 0.021%

    No Known Activations