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

    Neuronpedia

    INDEX
    Explanations

    difficulty and frustration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    觫
    0.48
    ك
    0.47
    рама
    0.47
    shakes
    0.46
    른
    0.44
    хи
    0.43
    saint
    0.43
     choć
    0.42
    plants
    0.42
     sekt
    0.42
    POSITIVE LOGITS
     Associate
    0.46
    avana
    0.45
     网
    0.43
     doanh
    0.43
     Publish
    0.42
    embangkan
    0.42
    indazol
    0.42
     Diy
    0.41
     Ngoài
    0.41
     إنشاء
    0.41
    Act Density 0.002%

    No Known Activations