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

    Neuronpedia

    INDEX
    Explanations

    hello there and what follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ش
    1.21
    شون
    1.09
    なります
    1.07
    1.03
    njih
    1.02
    衷
    1.02
     ज़रूरत
    1.01
    nelly
    0.99
    smouth
    0.99
    ästä
    0.98
    POSITIVE LOGITS
    лі
    1.03
    곳
    0.98
    тар
    0.97
    ய்
    0.95
    ра
    0.91
     Aenean
    0.90
    书
    0.89
    ಂಟ
    0.88
    れば
    0.88
    밑
    0.86
    Act Density 0.002%

    No Known Activations