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

    Neuronpedia

    INDEX
    Explanations

    innovations and advances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     」,
    0.46
    竑
    0.46
    嗉
    0.46
    леге
    0.44
    の方は
    0.44
     Pred
    0.43
    科
    0.43
    ពិ
    0.43
    を設定
    0.43
    പരി
    0.42
    POSITIVE LOGITS
    t
    0.49
     son
    0.46
    h
    0.45
    sibling
    0.44
    b
    0.44
     brother
    0.43
    hilt
    0.43
    s
    0.42
     womb
    0.41
     proverb
    0.41
    Act Density 0.003%

    No Known Activations