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

    Neuronpedia

    INDEX
    Explanations

    white in different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DARK
    0.70
    Dark
    0.68
     dark
    0.66
     Dark
    0.64
     DARK
    0.61
    blackberry
    0.61
    Purple
    0.59
     darker
    0.59
    dark
    0.57
     шокола
    0.55
    POSITIVE LOGITS
     white
    2.16
    white
    2.00
    白
    1.89
    White
    1.87
     White
    1.87
     WHITE
    1.87
     белый
    1.82
    WHITE
    1.80
     सफेद
    1.77
    白色
    1.77
    Act Density 0.131%

    No Known Activations