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

    Neuronpedia

    INDEX
    Explanations

    lungs, chest, body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ین
    2.53
    но
    1.61
    тов
    1.59
    сть
    1.58
    ти
    1.55
    𝙨
    1.43
    𝘀
    1.40
     добавлен
    1.39
     αποτέ
    1.39
    ка
    1.38
    POSITIVE LOGITS
    m
    2.11
    N
    1.61
    A
    1.56
    IVITY
    1.55
    munk
    1.54
    EL
    1.52
    y
    1.52
    و
    1.52
    IDENCE
    1.49
    ให้
    1.47
    Act Density 0.001%

    No Known Activations