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

    Neuronpedia

    INDEX
    Explanations

    scene introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    çe
    0.50
     começou
    0.44
     conto
    0.44
     miserable
    0.43
     passar
    0.42
     corrupción
    0.42
     quadrato
    0.41
    incia
    0.41
    čila
    0.41
     acho
    0.40
    POSITIVE LOGITS
    ielles
    0.46
    rün
    0.44
    NEW
    0.42
     آنلاین
    0.41
     NEW
    0.40
     Notifications
    0.39
    评分
    0.38
     уведом
    0.38
     तसेच
    0.38
     Shenzhen
    0.38
    Act Density 0.001%

    No Known Activations