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

    Neuronpedia

    INDEX
    Explanations

    Firstly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Си
    1.85
    લા
    1.85
     eng
    1.74
    Пре
    1.74
    Дан
    1.68
    Ла
    1.67
    Бы
    1.67
    Changing
    1.65
    𝑟
    1.62
    Latch
    1.61
    POSITIVE LOGITS
    nikiem
    1.97
    ேத்க
    1.87
    癀
    1.85
     букмекерлер
    1.83
    دق
    1.75
    től
    1.72
    ேஷ்
    1.72
    itius
    1.63
    roads
    1.62
    ných
    1.62
    Act Density 0.000%

    No Known Activations