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

    Neuronpedia

    INDEX
    Explanations

    ios fs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𪤗
    -0.07
     \↵
    -0.06
    생
    -0.06
    Û
    -0.06
    褛
    -0.06
    levard
    -0.06
    闻
    -0.06
    ⽣
    -0.06
    _$
    -0.06
     sự
    -0.06
    POSITIVE LOGITS
     السياسي
    0.07
     reclaim
    0.07
    )"},↵
    0.07
     تحديث
    0.07
    のでしょうか
    0.07
     назад
    0.07
    centers
    0.07
    ...............
    0.07
     судеб
    0.07
     hacked
    0.06
    Act Density 0.001%

    No Known Activations