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

    Neuronpedia

    INDEX
    Explanations

    references to sizes and quantities in various contexts

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

    size and complexity of entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.56
    ьаж
    -0.50
     CreateTagHelper
    -0.47
    rouvez
    -0.46
    saraba
    -0.45
     surla
    -0.44
     podjela
    -0.43
    antaranya
    -0.42
    MemoryWarning
    -0.41
    لكتر
    -0.40
    POSITIVE LOGITS
    Демографія
    0.49
     villages
    0.43
     factories
    0.43
     museums
    0.42
     vegetarians
    0.41
     Moines
    0.41
    ForValue
    0.41
     ſmall
    0.40
     lesbians
    0.40
     towns
    0.40
    Act Density 0.034%

    No Known Activations