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

    Neuronpedia

    INDEX
    Explanations

    best award category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اویز
    0.56
     lente
    0.42
     tailles
    0.41
     precede
    0.40
     tamaños
    0.40
    atypes
    0.39
    تباينه
    0.38
     exemples
    0.37
     passent
    0.37
     declaraciones
    0.36
    POSITIVE LOGITS
     Best
    1.27
    Best
    1.23
     best
    1.09
     बेस्ट
    1.09
    best
    1.05
     सर्वश्रेष्ठ
    1.05
    Луч
    1.05
     лучший
    1.04
    最佳
    1.02
     луч
    0.97
    Act Density 0.018%

    No Known Activations