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

    Neuronpedia

    INDEX
    Explanations

    references to physical locations and placements within a space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    locations and prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     involvement
    -0.44
     kaarangay
    -0.43
     للاسماء
    -0.42
     Aristote
    -0.39
     vícti
    -0.39
    Aws
    -0.37
     iſt
    -0.37
    GraphicsUnit
    -0.36
    popper
    -0.36
     vek
    -0.36
    POSITIVE LOGITS
     rooms
    0.59
    RenderAtEndOf
    0.58
     lobby
    0.52
    +#+#
    0.51
     bathrooms
    0.50
     hallways
    0.50
    DockStyle
    0.50
     room
    0.48
     Rooms
    0.48
     toilet
    0.47
    Act Density 0.018%

    No Known Activations