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

    Neuronpedia

    INDEX
    Explanations

    hotel room types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    晟
    0.39
     grammaticality
    0.39
     संश्
    0.38
     ngữ
    0.37
     molécule
    0.37
     évaluations
    0.36
     princípios
    0.36
     LongNumber
    0.36
     distrust
    0.36
    HINSTANCE
    0.35
    POSITIVE LOGITS
     rooms
    1.40
     room
    1.24
    房間
    1.16
     Rooms
    1.16
    部屋
    1.15
     suites
    1.13
    Rooms
    1.13
     Room
    1.08
    房间
    1.08
    Room
    1.07
    Act Density 0.006%

    No Known Activations