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

    Neuronpedia

    INDEX
    Explanations

    symbols, denoted by, written as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     berbasis
    0.43
    alop
    0.43
     ethnicity
    0.42
    хин
    0.41
     عالمی
    0.40
     арифмети
    0.40
     الحصه
    0.40
    浃
    0.40
     ойнотуу
    0.39
     Ethnicity
    0.39
    POSITIVE LOGITS
    L
    0.50
     one
    0.47
     D
    0.44
     the
    0.43
     by
    0.43
    we
    0.43
    PL
    0.42
    use
    0.42
    後
    0.42
     co
    0.41
    Act Density 0.004%

    No Known Activations