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

    Neuronpedia

    INDEX
    Explanations

    proprietary systems or technologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    с
    2.03
    ب
    1.87
    то
    1.84
    魄
    1.68
    сний
    1.45
    د
    1.43
    де
    1.41
    ка
    1.39
    че
    1.39
    баты
    1.38
    POSITIVE LOGITS
    Мы
    1.63
    ar
    1.59
     Ее
    1.59
    YC
    1.51
    ي
    1.51
    Polar
    1.47
     conceitos
    1.47
    Leia
    1.47
    Bueno
    1.44
    Porsche
    1.43
    Act Density 0.017%

    No Known Activations