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

    Neuronpedia

    INDEX
    Explanations

    language and life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    হইল
    0.37
    اکي
    0.35
    靂
    0.34
    ಸ್ಕೊ
    0.34
    餑
    0.34
     因為
    0.34
     學
    0.34
    ဤ
    0.34
    蘞
    0.34
    瀏覽
    0.33
    POSITIVE LOGITS
    を
    0.46
    に
    0.44
    の
    0.42
    0.42
    が
    0.40
    ,
    0.40
    를
    0.37
     m
    0.35
     to
    0.35
     "
    0.35
    Act Density 0.006%

    No Known Activations