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

    Neuronpedia

    INDEX
    Explanations

    white

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     VARIABLES
    0.41
    赤い
    0.41
    െങ്ക
    0.40
    বৃত্ত
    0.40
     ними
    0.40
     entidade
    0.38
    엿
    0.38
    zechoslovakia
    0.37
    ان
    0.37
    ariamente
    0.37
    POSITIVE LOGITS
     white
    1.34
    white
    1.23
     fehér
    1.23
    White
    1.23
     White
    1.22
    白
    1.20
     白
    1.17
    白的
    1.13
     ホワイト
    1.05
     beyaz
    1.05
    Act Density 0.017%

    No Known Activations