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

    Neuronpedia

    INDEX
    Explanations

    numbers and chess notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的标准
    0.46
    alling
    0.43
     χρησιμοποι
    0.43
    arse
    0.41
    ígenes
    0.41
    arks
    0.40
     Happened
    0.40
    riting
    0.40
     Ecusson
    0.40
    ;
    0.40
    POSITIVE LOGITS
    ۰
    0.51
    0
    0.49
    ה
    0.47
    در
    0.46
    ﺖ
    0.45
    Tại
    0.45
    ا
    0.45
    ປະ
    0.44
     privado
    0.44
    )_{
    0.43
    Act Density 0.007%

    No Known Activations