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

    Neuronpedia

    INDEX
    Explanations

    mix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chuyên
    -0.06
    訊
    -0.06
    ر
    -0.06
     protestors
    -0.06
    벽
    -0.06
    <$
    -0.06
    ालय
    -0.06
    ů
    -0.06
    皇
    -0.05
    ado
    -0.05
    POSITIVE LOGITS
     */↵↵↵↵
    0.07
    gy
    0.07
    区域
    0.07
     Abdullah
    0.07
    -org
    0.07
     Sin
    0.07
     setValue
    0.07
    //------------------------------------------------------------------------------↵
    0.07
     Vac
    0.07
     방송
    0.07
    Act Density 0.017%

    No Known Activations