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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     açısından
    -0.07
    红豆
    -0.07
    冕
    -0.07
    向
    -0.07
     Cannon
    -0.07
    轻
    -0.06
    /values
    -0.06
    倒塌
    -0.06
    青蛙
    -0.06
    vertices
    -0.06
    POSITIVE LOGITS
    Maker
    0.08
     zrobić
    0.07
    ="">
    0.07
     zostać
    0.07
    Reality
    0.07
    LOGY
    0.07
    帮忙
    0.07
    _RANDOM
    0.07
    "—
    0.06
    考
    0.06
    Act Density 0.000%

    No Known Activations