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

    Neuronpedia

    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erna
    -0.07
     irony
    -0.07
    ropped
    -0.07
    ladık
    -0.06
    jím
    -0.06
    です
    -0.06
    КИ
    -0.06
    ワイト
    -0.06
    /crypto
    -0.06
     fries
    -0.06
    POSITIVE LOGITS
     stopping
    0.07
     alph
    0.06
     indict
    0.06
    一个
    0.06
    аб
    0.06
     pueden
    0.06
     versus
    0.06
     SOUR
    0.06
    }↵↵↵↵↵
    0.06
     Мин
    0.06
    Act Density 0.034%

    No Known Activations