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

    Neuronpedia

    INDEX
    Explanations

    gu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     πο
    -0.07
    曲
    -0.07
     Zahl
    -0.06
     Pikachu
    -0.06
     makes
    -0.06
     쇼
    -0.06
    육
    -0.06
    positor
    -0.06
     真
    -0.06
    وح
    -0.06
    POSITIVE LOGITS
    れて
    0.08
    šť
    0.07
    ague
    0.07
    Ctrls
    0.07
    199
    0.06
    ajs
    0.06
    ुए
    0.06
     Guy
    0.06
     Homepage
    0.06
    開発
    0.06
    Act Density 0.019%

    No Known Activations