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

    Neuronpedia

    INDEX
    Explanations

    utterly unremarkable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    assuming
    0.39
     brasileiro
    0.39
    ycle
    0.38
    umping
    0.38
     цих
    0.38
    omme
    0.37
     ہر
    0.37
     चक्र
    0.37
     Attractions
    0.37
    ufa
    0.36
    POSITIVE LOGITS
    女神
    0.43
    േഷ
    0.39
     क्योंकि
    0.38
     ибо
    0.37
     Notably
    0.37
    沫
    0.37
    деб
    0.36
     Schen
    0.36
     Cud
    0.36
     требованиям
    0.35
    Act Density 0.000%

    No Known Activations