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

    Neuronpedia

    INDEX
    Explanations

    Vietnamese words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     яе
    0.59
    літы
    0.54
    краё
    0.54
    кансер
    0.54
     аўтаматы
    0.52
     Расійскай
    0.52
     бясплат
    0.52
     Гуляць
    0.52
    Კ
    0.51
    ўным
    0.51
    POSITIVE LOGITS
     trong
    0.64
     khi
    0.62
     đ
    0.61
     có
    0.61
     một
    0.60
     Đ
    0.60
     d
    0.59
     về
    0.59
     liên
    0.59
     th
    0.59
    Act Density 0.001%

    No Known Activations