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

    Neuronpedia

    INDEX
    Explanations

    sudden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2.09
    farbe
    1.87
    storms
    1.83
    1.81
    𝑃
    1.80
     iria
    1.80
    esquerdo
    1.78
    纂
    1.74
     هنگام
    1.71
    רים
    1.71
    POSITIVE LOGITS
    Carousel
    1.58
     generando
    1.56
     sop
    1.47
     tense
    1.43
    ّ
    1.41
    ธ์
    1.40
     anger
    1.35
    цца
    1.35
    ormal
    1.33
    ያ
    1.32
    Act Density 0.001%

    No Known Activations