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

    Neuronpedia

    INDEX
    Explanations

    videos, hand, specializes, lottery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {\'
    0.45
     نفسك
    0.41
    িয়৷
    0.36
     ကျွန်
    0.36
     silvest
    0.36
     flavoured
    0.35
    cwd
    0.35
     flavour
    0.35
     kulturn
    0.34
     giveaways
    0.34
    POSITIVE LOGITS
    Ку
    0.40
    チ
    0.40
    ЛА
    0.40
    Ба
    0.38
    Так
    0.37
    зи
    0.37
    ச்சியை
    0.37
    АН
    0.37
    ной
    0.36
     Yani
    0.36
    Act Density 0.036%

    No Known Activations