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

    Neuronpedia

    INDEX
    Explanations

    not a single reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FIB
    0.36
     động
    0.35
     interferes
    0.35
     využ
    0.33
     AND
    0.33
    変更
    0.33
     catalyzes
    0.33
     editing
    0.32
     IconButton
    0.32
    流动
    0.32
    POSITIVE LOGITS
     однозна
    0.63
     sempurna
    0.62
    完美的
    0.61
     conclusively
    0.58
    完璧
    0.58
    完美
    0.57
     guarantee
    0.56
     гаранти
    0.55
     infallible
    0.55
     गारंटी
    0.55
    Act Density 0.465%

    No Known Activations