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

    Neuronpedia

    INDEX
    Explanations

    onError

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NUnit
    -0.08
    Supplier
    -0.07
     tertiary
    -0.07
     spokesman
    -0.07
    firstname
    -0.06
     ignorant
    -0.06
    �
    -0.06
    货架
    -0.06
    的概率
    -0.06
     يبدو
    -0.06
    POSITIVE LOGITS
    癫痫病
    0.07
    ഗ
    0.07
     cljs
    0.07
     numeros
    0.06
     леч
    0.06
    cych
    0.06
     kafka
    0.06
    tür
    0.06
    ;"><?
    0.06
    会员
    0.06
    Act Density 0.003%

    No Known Activations