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

    Neuronpedia

    INDEX
    Explanations

    Native American peoples and cultures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ६
    0.78
     jaoks
    0.73
    πα
    0.71
    க்கு
    0.70
    4
    0.69
    ۳
    0.69
    ਫ
    0.67
    np
    0.66
     패
    0.66
    도
    0.65
    POSITIVE LOGITS
    ad
    1.25
    the
    1.00
    el
    0.94
    w
    0.90
    d
    0.89
     is
    0.88
    ла
    0.83
     for
    0.82
    ul
    0.82
    ↵
    0.81
    Act Density 0.001%

    No Known Activations