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

    Neuronpedia

    INDEX
    Explanations

    more quantity or roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    梏
    0.77
     মারা
    0.74
    下滑
    0.73
    ımıza
    0.72
    ╿
    0.72
    лик
    0.72
     Specify
    0.70
    めに
    0.70
    ঞ্চলে
    0.70
     Chọn
    0.69
    POSITIVE LOGITS
     much
    1.28
     mucho
    1.20
    much
    1.17
     beaucoup
    1.12
     MUCH
    1.11
     muchísimo
    1.09
    more
    1.07
     أكثر
    1.06
     more
    1.06
     многое
    1.00
    Act Density 0.006%

    No Known Activations