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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lesson
    -0.07
    🤛
    -0.07
    Essay
    -0.07
    有點
    -0.07
    Section
    -0.07
    创造了
    -0.07
     instead
    -0.06
    .''
    -0.06
    下次
    -0.06
     Transactions
    -0.06
    POSITIVE LOGITS
    绷
    0.08
    ela
    0.08
    :";
↵
    0.07
    rnd
    0.07
    鹦
    0.07
     chute
    0.07
    &eacute
    0.07
    ">&#
    0.07
    emie
    0.07
    肼
    0.07
    Act Density 0.001%

    No Known Activations