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

    Neuronpedia

    INDEX
    Explanations

    'will vary' or 'can be'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dengan
    1.20
    स्परिक
    1.16
    २
    1.15
    λά
    1.12
    یدم
    1.11
    стья
    1.09
    asmuch
    1.08
     Semua
    1.08
    Раз
    1.06
    ﺁ
    1.06
    POSITIVE LOGITS
     poter
    1.02
    ש
    1.02
    ে
    1.00
    i
    0.98
    選択
    0.98
    できるよう
    0.93
    ು
    0.93
     riport
    0.91
     requ
    0.91
     deflation
    0.91
    Act Density 0.361%

    No Known Activations