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

    Neuronpedia

    INDEX
    Explanations

    rooms and amenities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мероприя
    0.42
     страну
    0.42
     недалеко
    0.42
     вечером
    0.42
     cak
    0.39
     Спорттук
    0.39
     "#{@
    0.39
     తన
    0.38
     pantai
    0.38
     месте
    0.38
    POSITIVE LOGITS
    空调
    0.42
    液晶
    0.41
    它们
    0.40
    它們
    0.40
    梳
    0.38
    اتی
    0.38
    瓷
    0.36
    yled
    0.36
    它们的
    0.36
    ات
    0.35
    Act Density 0.001%

    No Known Activations