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

    Neuronpedia

    INDEX
    Explanations

    Chinese Pinyin and characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     гульнявыя
    0.58
    愊
    0.57
    𝒍
    0.57
    Раз
    0.52
    таў
    0.51
    㣩
    0.51
    біць
    0.50
    瘘
    0.50
    捙
    0.50
     Стаўкі
    0.50
    POSITIVE LOGITS
     ép
    0.45
     quan
    0.43
    úng
    0.43
     Liao
    0.42
    量
    0.42
    ép
    0.41
     ※
    0.39
    ương
    0.38
     qí
    0.37
    ່
    0.37
    Act Density 0.014%

    No Known Activations