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

    Neuronpedia

    INDEX
    Explanations

    finding leads to outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    詬
    0.34
    োহণ
    0.33
     পুনরুদ্ধার
    0.31
     منتقل
    0.30
     क्षतिग्रस्त
    0.30
     എന്റെ
    0.30
    菈
    0.29
     Гуляць
    0.29
    殮
    0.29
     ഉപകരണ
    0.29
    POSITIVE LOGITS
    if
    0.38
    e
    0.30
    W
    0.30
    |
    0.29
     an
    0.29
    Be
    0.29
     more
    0.28
     a
    0.27
     be
    0.27
    Red
    0.27
    Act Density 0.001%

    No Known Activations