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

    Neuronpedia

    INDEX
    Explanations

    specific room contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ్యాచ్
    0.43
     rejet
    0.37
     החד
    0.36
    ريط
    0.35
    🍙
    0.35
     ステン
    0.34
     cholesterol
    0.34
    द्दल
    0.34
    ಢ
    0.34
    蓣
    0.33
    POSITIVE LOGITS
     room
    4.41
    Room
    3.95
     Room
    3.88
    room
    3.81
     rooms
    3.81
     ROOM
    3.75
    房间
    3.56
     Rooms
    3.41
    ROOM
    3.41
    房間
    3.41
    Act Density 0.094%

    No Known Activations