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

    Neuronpedia

    INDEX
    Explanations

    a followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.50
     attested
    0.42
     أق
    0.41
    ↵
    0.39
     संसा
    0.38
    ан
    0.37
     individualized
    0.37
     ద్వారా
    0.37
     histoire
    0.37
     ambivalent
    0.37
    POSITIVE LOGITS
    i
    0.51
    この
    0.42
    み
    0.41
    Ｉ
    0.36
    大
    0.36
     I
    0.35
    ﮈ
    0.35
    ي
    0.35
    が
    0.34
    できる
    0.34
    Act Density 0.718%

    No Known Activations