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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "the world."

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

    teach the world to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lorette
    -0.42
    intios
    -0.42
    -------------</
    -0.40
     Reverso
    -0.40
     pem
    -0.39
    HideFlags
    -0.39
    lceil
    -0.38
     Jew
    -0.38
     noDo
    -0.37
    着
    -0.37
    POSITIVE LOGITS
     world
    0.65
     mundo
    0.59
     wereld
    0.59
    world
    0.57
     düny
    0.57
     dunia
    0.54
     dünya
    0.54
     दुनिया
    0.53
     vilá
    0.53
     المعيارى
    0.53
    Act Density 0.018%

    No Known Activations