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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Blade
    -0.07
     upgrades
    -0.06
    用于
    -0.06
     cognition
    -0.06
     Angel
    -0.06
     bef
    -0.06
    夜
    -0.06
    orton
    -0.06
    嗯
    -0.06
     bible
    -0.06
    POSITIVE LOGITS
    .GUI
    0.07
    ós
    0.07
     InvalidOperationException
    0.07
     nominate
    0.06
    urity
    0.06
     noexcept
    0.06
    UIApplication
    0.06
    refix
    0.06
    زی
    0.06
     اگر
    0.06
    Act Density 0.008%

    No Known Activations