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

    Neuronpedia

    INDEX
    Explanations

    descriptive elements related to architecture and physical spaces

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

    "ceiling" and "wall"

    np_acts-logits-general · gemini-2.0-flash

    hanging above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputTagHelper
    -0.57
     }{@
    -0.56
    tative
    -0.52
    bage
    -0.52
    Carex
    -0.51
     Carab
    -0.49
    पया
    -0.48
    invokeLater
    -0.48
    nito
    -0.47
    umbag
    -0.47
    POSITIVE LOGITS
     ceiling
    1.85
     ceilings
    1.69
     Ceiling
    1.54
    ceiling
    1.49
     walls
    1.48
     wall
    1.38
    Ceiling
    1.36
     plafond
    1.29
     Walls
    1.25
    walls
    1.18
    Act Density 0.146%

    No Known Activations