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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    表决
    -0.07
    ,)
    -0.07
     dw
    -0.07
    śmy
    -0.07
    żeli
    -0.07
    )'),↵
    -0.06
    寂静
    -0.06
     Worksheet
    -0.06
     Thị
    -0.06
     Verd
    -0.06
    POSITIVE LOGITS
    梯
    0.07
    原
    0.07
    빵
    0.06
    compressed
    0.06
    aders
    0.06
    _gray
    0.06
    уч
    0.06
    ″
    0.06
    coat
    0.06
    옥
    0.06
    Act Density 0.277%

    No Known Activations