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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     כיצ
    -0.08
     resultat
    -0.07
    weets
    -0.07
     dela
    -0.07
    迕
    -0.07
    تحويل
    -0.06
    Turn
    -0.06
    たり
    -0.06
    ڄ
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    _Array
    0.08
    就是为了
    0.08
     applauded
    0.07
    .window
    0.07
    ＊
    0.07
    ＾
    0.07
    _semaphore
    0.07
     Sodium
    0.07
    [unit
    0.07
     finden
    0.07
    Act Density 0.008%

    No Known Activations