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

    Neuronpedia

    INDEX
    Explanations

    alternatives or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Якщо
    0.46
    ሁሉም
    0.41
     почти
    0.41
    Все
    0.39
     километ
    0.39
    Nếu
    0.38
     바꿔
    0.38
     wszystkie
    0.38
     אם
    0.38
     augmente
    0.38
    POSITIVE LOGITS
    或其他
    0.66
     ataupun
    0.62
     কিংবা
    0.50
     maupun
    0.49
     or
    0.47
    或是
    0.47
     বা
    0.46
     atau
    0.46
     ή
    0.46
     veya
    0.46
    Act Density 0.110%

    No Known Activations