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

    Neuronpedia

    INDEX
    Explanations

    also called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    2.19
    ה
    2.05
    ATION
    2.00
     그래도
    2.00
    Saat
    1.99
    ある
    1.85
    IVE
    1.78
    =
    1.77
    itting
    1.75
    ORY
    1.73
    POSITIVE LOGITS
     불구하고
    2.52
     кстати
    2.17
     ведь
    1.91
    ال
    1.78
     преимуще
    1.77
     ভিত্তিতে
    1.77
     menores
    1.74
     불구
    1.74
     keď
    1.68
    ਡੀ
    1.65
    Act Density 0.077%

    No Known Activations