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

    Neuronpedia

    INDEX
    Explanations

    list all factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    と同様
    0.46
    nji
    0.42
     два
    0.42
     及び
    0.40
    を中心
    0.40
    AndView
    0.39
     ሁለት
    0.39
    ensed
    0.38
     zwei
    0.38
    TAGE
    0.38
    POSITIVE LOGITS
     Going
    0.45
     Pem
    0.40
     Become
    0.40
     Fuller
    0.39
     Lack
    0.39
     Mick
    0.38
     Nick
    0.38
     Those
    0.38
     Herv
    0.38
     cần
    0.37
    Act Density 0.003%

    No Known Activations