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

    Neuronpedia

    INDEX
    Explanations

    code identifiers and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Colored
    0.49
     Цвет
    0.43
     色
    0.42
     Farbe
    0.42
     Color
    0.41
     цвет
    0.41
     Coloring
    0.40
     AT
    0.40
    ARMA
    0.40
    @@
    0.39
    POSITIVE LOGITS
    ريب
    0.39
    pregn
    0.39
     pws
    0.38
    ржа
    0.37
    yra
    0.37
     trận
    0.37
    abilia
    0.36
     hrane
    0.36
    ساعد
    0.35
    нное
    0.35
    Act Density 0.000%

    No Known Activations