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

    Neuronpedia

    INDEX
    Explanations

    you do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    blogger
    0.42
    cour
    0.41
    lovak
    0.40
    çı
    0.38
    న్నో
    0.38
    tha
    0.38
     rendering
    0.38
     cardboard
    0.38
     illustration
    0.37
     illustrations
    0.37
    POSITIVE LOGITS
     μπορούν
    0.44
     দেবেন
    0.42
    入れて
    0.42
     محدود
    0.41
    入れる
    0.41
    を入れて
    0.40
     ridurre
    0.40
    哣
    0.39
     استف
    0.39
     Bankr
    0.39
    Act Density 0.002%

    No Known Activations