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

    Neuronpedia

    INDEX
    Explanations

    opposite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avin
    -0.09
     predictive
    -0.08
     الجنسية
    -0.08
     њ
    -0.08
     Wolves
    -0.08
    ogat
    -0.08
     dezelfde
    -0.07
     Luxembourg
    -0.07
     heterosexual
    -0.07
     sozialen
    -0.07
    POSITIVE LOGITS
     passieren
    0.08
     springs
    0.08
     расстоя
    0.08
     взять
    0.07
     rất
    0.07
     yönt
    0.07
     запуск
    0.07
     spring
    0.07
     lec
    0.07
    IEF
    0.07
    Act Density 0.004%

    No Known Activations