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

    Neuronpedia

    INDEX
    Explanations

    loop variable 'i'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    झे
    0.38
     overcrow
    0.38
    ൾ
    0.38
    ∨
    0.37
    єдна
    0.37
    АН
    0.35
     proie
    0.35
    獅
    0.35
    鸪
    0.35
    。<
    0.34
    POSITIVE LOGITS
     رجسٹریشن
    0.46
    incremental
    0.43
    alkyl
    0.41
    elementary
    0.40
     제조업
    0.40
    typedef
    0.40
    hip
    0.38
     flexible
    0.38
     فیصلے
    0.38
     terminé
    0.38
    Act Density 0.001%

    No Known Activations