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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     каче
    -0.07
    <List
    -0.07
     biz
    -0.06
    cono
    -0.06
    (shell
    -0.06
     simulator
    -0.06
     budding
    -0.06
    :expr
    -0.06
     Password
    -0.06
    ٔ
    -0.06
    POSITIVE LOGITS
    倫
    0.07
    حي
    0.07
    ائية
    0.07
    ικό
    0.06
    لي
    0.06
    ریک
    0.06
     техничес
    0.06
    ني
    0.06
    Outputs
    0.06
    伦
    0.06
    Act Density 0.225%

    No Known Activations