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

    Neuronpedia

    INDEX
    Explanations

    HLDiff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alojamiento
    0.45
    тические
    0.44
     आरोग
    0.43
    Бе
    0.42
     продук
    0.42
    friends
    0.42
     eureka
    0.41
     පුද්ග
    0.41
    produtos
    0.41
     hommage
    0.41
    POSITIVE LOGITS
     between
    0.48
     بين
    0.43
    他对
    0.43
     chased
    0.42
    between
    0.42
     invading
    0.42
     Each
    0.41
     encro
    0.41
     tubules
    0.40
    ড়
    0.40
    Act Density 0.003%

    No Known Activations