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

    Neuronpedia

    INDEX
    Explanations

    references to worlds or environments in a gaming context

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

    world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.44
     utafitiHapana
    -0.41
    └──
    -0.36
    AddTagHelper
    -0.35
    AndEndTag
    -0.35
     Administrativna
    -0.35
    Carriera
    -0.34
    ksesta
    -0.34
    ᅠ
    -0.34
    sstelle
    -0.33
    POSITIVE LOGITS
    world
    0.98
     world
    0.97
    World
    0.93
     World
    0.86
    WORLD
    0.84
     WORLD
    0.82
    getWorld
    0.73
    世界
    0.69
    ワールド
    0.65
    worlds
    0.65
    Act Density 0.000%

    No Known Activations