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

    Neuronpedia

    INDEX
    Explanations

    freeze while

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     그래서
    0.71
     olursa
    0.66
    が含ま
    0.66
    なければ
    0.66
    が必要です
    0.64
    とも
    0.64
    ાર્થના
    0.64
     رکھنے
    0.62
     عندك
    0.62
     مبنی
    0.61
    POSITIVE LOGITS
     while
    6.61
    while
    5.99
    While
    5.66
     While
    5.58
     whilst
    5.37
     mientras
    5.31
     WHILE
    5.18
     mentre
    5.18
     enquanto
    4.85
     Whilst
    4.36
    Act Density 1.221%

    No Known Activations