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

    Neuronpedia

    INDEX
    Explanations

    technical references to game world elements and instances

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

    world and room instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.75
    ValueStyle
    -0.75
    IndentedString
    -0.74
    ArrowToggle
    -0.73
     ProtoMessage
    -0.71
    richTextPanel
    -0.71
    elemField
    -0.70
    InitVars
    -0.69
    PerformLayout
    -0.68
    webElementXpaths
    -0.68
    POSITIVE LOGITS
    getWorld
    0.57
     environment
    0.56
    World
    0.55
     Environment
    0.53
     World
    0.51
    world
    0.49
     world
    0.47
     Umwelt
    0.46
    WORLD
    0.41
     environments
    0.40
    Act Density 0.004%

    No Known Activations