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

    Neuronpedia

    INDEX
    Explanations

    Online comments/posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Viol
    -0.07
     ماي
    -0.07
    Name
    -0.07
     잠
    -0.07
     Analytics
    -0.07
    ätze
    -0.07
    措施
    -0.06
     toi
    -0.06
     boxing
    -0.06
    atz
    -0.06
    POSITIVE LOGITS
    _ot
    0.06
     chased
    0.06
    ör
    0.06
    loan
    0.06
     tapping
    0.05
    _funcs
    0.05
     productService
    0.05
    ли
    0.05
    カテゴリ
    0.05
     espec
    0.05
    Act Density 0.027%

    No Known Activations