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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fire
    -0.07
    _brightness
    -0.07
     admon
    -0.07
    的隱私權
    -0.07
     slashing
    -0.07
    -known
    -0.07
    嫣
    -0.06
    扞
    -0.06
     tug
    -0.06
    :n
    -0.06
    POSITIVE LOGITS
    "{
    0.08
    .getInt
    0.07
    零部件
    0.07
    力
    0.07
    排出
    0.07
     realizado
    0.07
     victorious
    0.07
    Detailed
    0.07
    0.07
    less
    0.07
    Act Density 0.049%

    No Known Activations