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

    Neuronpedia

    INDEX
    Explanations

    room

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ndvi
    0.73
    henol
    0.70
    🌯
    0.68
    Casc
    0.67
    hiyan
    0.67
    髭
    0.64
    andaş
    0.63
     Hines
    0.63
    鍔
    0.62
     हार्दिक
    0.62
    POSITIVE LOGITS
     room
    5.63
     rooms
    5.15
     Room
    5.07
    Room
    4.97
    room
    4.76
     ROOM
    4.58
     Rooms
    4.53
    Rooms
    4.36
    ROOM
    4.26
    房间
    4.26
    Act Density 0.264%

    No Known Activations