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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tầm
    -0.07
     عامل
    -0.07
     المغ
    -0.07
    grey
    -0.06
     prejudice
    -0.06
     पढ़
    -0.06
     Goat
    -0.06
    лат
    -0.06
    .did
    -0.06
     Fern
    -0.06
    POSITIVE LOGITS
    활
    0.06
     Hok
    0.06
    支付
    0.06
     unicode
    0.06
     환
    0.06
    callbacks
    0.06
     scipy
    0.06
     kako
    0.06
    autoplay
    0.06
     Computer
    0.06
    Act Density 0.052%

    No Known Activations