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

    Neuronpedia

    INDEX
    Explanations

    in what ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ように
    1.88
    们
    1.63
    ようになりました
    1.49
    {
    1.48
    いた
    1.44
     sebagainya
    1.41
    🔥🔥
    1.41
    よう
    1.40
    قبل
    1.39
    决心
    1.39
    POSITIVE LOGITS
    ا
    2.56
    ן
    2.45
    র
    2.31
    l
    2.20
    u
    2.16
    ு
    2.05
    n
    2.03
    ن
    2.02
    י
    1.96
    m
    1.95
    Act Density 0.010%

    No Known Activations