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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Precision
    -0.07
    综合实力
    -0.07
     fare
    -0.07
     +↵↵
    -0.07
    שמר
    -0.06
    (GET
    -0.06
    老子
    -0.06
     restrictive
    -0.06
    [maxn
    -0.06
    że
    -0.06
    POSITIVE LOGITS
    튕
    0.09
    ائل
    0.07
     squ
    0.07
     sağlayan
    0.07
     surrounding
    0.07
    妨
    0.07
     Zip
    0.07
     гаранти
    0.07
    �
    0.07
    晃
    0.06
    Act Density 0.009%

    No Known Activations