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

    Neuronpedia

    INDEX
    Explanations

    auto-generated code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SER
    -0.07
    sth
    -0.06
     button
    -0.06
     Addr
    -0.06
    وین
    -0.06
    -hook
    -0.06
     lint
    -0.06
    /NĐ
    -0.06
    birth
    -0.06
    Center
    -0.06
    POSITIVE LOGITS
     продукты
    0.09
    َو
    0.07
    레이
    0.07
     开始
    0.07
     panic
    0.06
     toxic
    0.06
     сегодня
    0.06
    Campo
    0.06
     اسلام
    0.06
    (';
    0.06
    Act Density 0.003%

    No Known Activations