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

    Neuronpedia

    INDEX
    Explanations

    living room

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    碑
    0.72
    髭
    0.71
    土壤
    0.68
    henol
    0.68
    ขับ
    0.67
    蜞
    0.66
    اعدة
    0.62
    䣼
    0.62
    🌯
    0.62
    MBean
    0.62
    POSITIVE LOGITS
     rooms
    4.94
     room
    4.93
     Room
    4.44
    Room
    4.32
     Rooms
    4.24
    Rooms
    4.04
    room
    4.01
     ROOM
    3.97
    rooms
    3.91
    房间
    3.89
    Act Density 0.124%

    No Known Activations