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

    Neuronpedia

    INDEX
    Explanations

    product identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mismanagement
    0.44
     interdiscipl
    0.41
    議論
    0.40
     Kolmogorov
    0.40
     transcriptional
    0.39
     문제를
    0.39
     chapitre
    0.39
     postdoc
    0.38
     culp
    0.38
     hypothesized
    0.38
    POSITIVE LOGITS
     제품
    0.59
     fabricante
    0.57
    商品
    0.55
     prodotto
    0.55
     produktu
    0.54
    新品
    0.53
     товара
    0.53
     新品
    0.53
     ürün
    0.53
    สินค้า
    0.53
    Act Density 0.018%

    No Known Activations