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

    Neuronpedia

    INDEX
    Explanations

    references to vague or undefined objects or concepts, particularly those described using the word "thing" and its variations

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

    thing and informal spellings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CreateMap
    -0.42
    InjectAttribute
    -0.41
    enetrable
    -0.41
    ImageField
    -0.41
     ویکی‌آمباردا
    -0.40
    rungsseite
    -0.40
    epam
    -0.40
    assertRaises
    -0.39
    Brainz
    -0.39
     LCCN
    -0.39
    POSITIVE LOGITS
     thing
    1.62
     things
    1.56
     THING
    1.38
    things
    1.38
     Thing
    1.37
    Thing
    1.37
     THINGS
    1.32
     Things
    1.32
    Things
    1.29
    thing
    1.28
    Act Density 0.025%

    No Known Activations