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

    Neuronpedia

    INDEX
    Explanations

    thankfully there

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     droite
    1.23
    ির
    1.23
    ない
    1.16
     offre
    1.13
     Assass
    1.09
    ולה
    1.09
     bâtiments
    1.08
    ка
    1.07
     triệu
    1.06
    ك
    1.06
    POSITIVE LOGITS
    y
    1.22
    tedir
    1.16
    нде
    1.13
     принима
    1.13
    Codigo
    1.12
    دي
    1.11
    ведение
    1.11
    سور
    1.11
    ي
    1.10
     һ
    1.09
    Act Density 0.001%

    No Known Activations