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

    Neuronpedia

    INDEX
    Explanations

    Comcast/Xfinity customer service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يم
    0.57
     impoz
    0.54
     yearn
    0.53
    им
    0.52
     soothe
    0.51
     yearning
    0.50
     heim
    0.49
     planète
    0.49
    ی
    0.49
     humming
    0.49
    POSITIVE LOGITS
    ída
    0.57
    aupt
    0.50
    bor
    0.49
    vare
    0.48
    uelas
    0.48
    gs
    0.47
     चिंग
    0.47
    IBRARY
    0.46
    鐢
    0.46
    <blockquote>
    0.46
    Act Density 0.000%

    No Known Activations