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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aven
    -0.07
     Vick
    -0.06
    .nil
    -0.06
    .AddComponent
    -0.06
    vides
    -0.06
     stems
    -0.06
    _failure
    -0.06
     Prote
    -0.06
    _RAW
    -0.06
     inse
    -0.06
    POSITIVE LOGITS
     ﾊ
    0.07
    厂
    0.06
    报名
    0.06
    ”.↵
    0.06
     Finance
    0.06
    .aspx
    0.06
     preliminary
    0.06
    岗
    0.06
    _()↵
    0.06
     рецепт
    0.06
    Act Density 0.000%

    No Known Activations