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

    Neuronpedia

    INDEX
    Explanations

    news reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    場合は
    -0.07
    typeof
    -0.07
    hib
    -0.06
    中国古代
    -0.06
    �
    -0.06
    啜
    -0.06
    ვ
    -0.06
    /us
    -0.06
    ﾊ
    -0.06
     quy
    -0.06
    POSITIVE LOGITS
     가지고
    0.08
     הכר
    0.07
    𝓁
    0.07
    angle
    0.07
    mented
    0.07
    いない
    0.07
    .format
    0.07
    _FACTOR
    0.07
    _changed
    0.07
    agos
    0.07
    Act Density 0.027%

    No Known Activations