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

    Neuronpedia

    INDEX
    Explanations

    Legal or formal reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    规模以上
    -0.07
     kick
    -0.07
    .fe
    -0.07
    万人
    -0.07
    君子
    -0.06
    アジア
    -0.06
    tório
    -0.06
     fifty
    -0.06
     Bros
    -0.06
    -B
    -0.06
    POSITIVE LOGITS
    智能制造
    0.08
     HttpRequest
    0.07
    IMAL
    0.07
    (serial
    0.07
    ’↵↵
    0.07
    _detect
    0.07
    ║
    0.07
    頻道
    0.07
    :".
    0.07
     '!
    0.06
    Act Density 0.019%

    No Known Activations