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

    Neuronpedia

    INDEX
    Explanations

    references to evidence or clues in a narrative context

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

    Parts of rooms (walls, floors, ceilings)

    np_acts-logits-general · gemini-2.0-flash

    walls, floors, and ceilings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     roadside
    -0.45
    styleable
    -0.41
     Attractive
    -0.39
     Kite
    -0.38
    δή
    -0.37
     Refuse
    -0.36
     Rejected
    -0.35
     Spazier
    -0.35
    tagext
    -0.35
    */].
    -0.34
    POSITIVE LOGITS
     rooms
    1.17
     room
    1.13
     floor
    1.11
     floors
    1.06
     ceiling
    1.01
     ceilings
    0.99
     interior
    0.98
     FLOOR
    0.98
    Floor
    0.97
    floor
    0.96
    Act Density 0.543%

    No Known Activations