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

    Neuronpedia

    INDEX
    Explanations

    is or are questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unteren
    0.79
    କୁ
    0.75
    টাতে
    0.72
    بانی
    0.70
    ವನ್ನು
    0.68
    ବା
    0.68
    Спасибо
    0.68
     BeautifulSoup
    0.67
     revolved
    0.67
     використову
    0.66
    POSITIVE LOGITS
    คือ
    1.09
     हैं
    1.08
     คือ
    1.06
     adalah
    0.99
     is
    0.99
    的是
    0.98
     are
    0.98
     হলো
    0.97
     है
    0.95
     jsou
    0.95
    Act Density 0.096%

    No Known Activations