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

    Neuronpedia

    INDEX
    Explanations

    eccentric contractions or eminent domain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    1.06
    к
    0.68
    ной
    0.67
    é
    0.67
    ul
    0.63
    yl
    0.63
    ку
    0.62
    ん
    0.61
    xc
    0.60
    w
    0.59
    POSITIVE LOGITS
     бір
    0.66
    出産
    0.66
     clashes
    0.64
          
    0.63
    บริการ
    0.63
     ਇੱਕ
    0.63
    야
    0.62
     کشاور
    0.61
     busting
    0.61
    襁
    0.61
    Act Density 0.001%

    No Known Activations