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

    Neuronpedia

    INDEX
    Explanations

    references to physical spaces or locations, particularly in domestic contexts

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

    Locations (rooms, buildings, areas)

    np_acts-logits-general · gemini-2.0-flash

    door and related architectural features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.82
    PerformLayout
    -0.79
     تضيفلها
    -0.68
     cherchés
    -0.68
    TagMode
    -0.68
    KommentareTeilen
    -0.64
     وتسجيلات
    -0.64
     onCancelled
    -0.64
    AndEndTag
    -0.64
    SBATCH
    -0.64
    POSITIVE LOGITS
     door
    0.83
     doors
    0.83
     dwellers
    0.75
     floor
    0.74
     area
    0.72
     walls
    0.72
    door
    0.72
     Door
    0.68
    Door
    0.66
     entrance
    0.61
    Act Density 0.239%

    No Known Activations