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

    Neuronpedia

    INDEX
    Explanations

    description of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FAV
    0.43
     फेव
    0.43
    ગાહી
    0.41
     faction
    0.39
     Promenade
    0.39
     किफायती
    0.38
     Notable
    0.38
     Abra
    0.38
     Location
    0.38
     Favorite
    0.37
    POSITIVE LOGITS
    eches
    0.41
    OutputStream
    0.39
     nooit
    0.38
    ชีวิต
    0.38
    phia
    0.38
    精力
    0.37
     трудно
    0.37
    ışt
    0.37
     systematics
    0.37
    дал
    0.36
    Act Density 0.000%

    No Known Activations