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

    Neuronpedia

    INDEX
    Explanations

    descriptions of locations within multi-story buildings, including their levels and spatial arrangements

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

    Ordinal numbers and "floor" or "floors"

    np_acts-logits-general · gemini-2.0-flash

    numbers indicating building floors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hamshire
    -0.63
    exitRule
    -0.62
    posedge
    -0.49
    ensement
    -0.48
    @[+][
    -0.47
     BorderSide
    -0.44
    řízení
    -0.44
     AssemblyProduct
    -0.43
     Viator
    -0.43
     jenner
    -0.42
    POSITIVE LOGITS
     floor
    2.63
     floors
    2.41
     Floor
    2.24
    floor
    2.20
    Floor
    2.10
     FLOOR
    2.07
     Floors
    1.92
    FLOOR
    1.84
    floors
    1.81
     storey
    1.61
    Act Density 0.185%

    No Known Activations