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

    Neuronpedia

    INDEX
    Explanations

    information because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eftersom
    0.65
     ибо
    0.63
     যেহেতু
    0.61
     поскольку
    0.60
     puisque
    0.60
     चूंकि
    0.58
     เนื่องจาก
    0.57
     deoarece
    0.56
     poiché
    0.55
     Поскольку
    0.55
    POSITIVE LOGITS
    ات
    0.35
     LE
    0.35
    ଛ
    0.34
     Филип
    0.33
    લી
    0.32
    ਿ
    0.32
     leave
    0.32
    лади
    0.32
     Ily
    0.32
     televisão
    0.32
    Act Density 0.042%

    No Known Activations