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

    Neuronpedia

    INDEX
    Explanations

    non-english text and characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uk
    0.64
    v
    0.59
    ok
    0.51
    f
    0.50
    b
    0.48
     positives
    0.47
    es
    0.45
    m
    0.45
    j
    0.45
    is
    0.45
    POSITIVE LOGITS
    ictwa
    0.47
     الشعر
    0.47
     इत्यादि
    0.46
     جغ
    0.45
     तप
    0.45
     কবিতা
    0.43
     أو
    0.43
    または
    0.43
     ਜ਼
    0.43
     بلکه
    0.43
    Act Density 0.003%

    No Known Activations