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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    勉强
    -0.08
    parallel
    -0.07
    .Children
    -0.07
     Likes
    -0.07
    .↵↵↵↵↵↵
    -0.07
    _NOP
    -0.07
    Defined
    -0.07
     как
    -0.07
    �
    -0.07
     NJ
    -0.07
    POSITIVE LOGITS
     replic
    0.07
    عنا
    0.07
     primitives
    0.07
     初始化
    0.07
    镬
    0.07
    От
    0.07
    ӧ
    0.07
     Glory
    0.07
     fruity
    0.07
    RetVal
    0.07
    Act Density 0.002%

    No Known Activations