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

    Neuronpedia

    INDEX
    Explanations

    don't want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.53
    an
    0.51
    as
    0.46
    n
    0.43
    re
    0.42
    m
    0.42
    esque
    0.42
    a
    0.41
    o
    0.41
    ic
    0.40
    POSITIVE LOGITS
    ंख्य
    0.45
    ตรฐาน
    0.44
    ভাবে
    0.42
    ى
    0.42
    বিভিন্ন
    0.41
    브
    0.41
    하다
    0.40
     ആണ്
    0.39
    크
    0.39
    ามารถ
    0.39
    Act Density 0.003%

    No Known Activations