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

    Neuronpedia

    INDEX
    Explanations

    quantifications that highlight the prevalence or dominance of certain groups or phenomena

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

    "majority" or "vast"

    np_acts-logits-general · gemini-2.0-flash

    vast majority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    withIdentifier
    -0.74
     <=",
    -0.66
    MemoryWarning
    -0.62
    __).
    -0.59
    PageContext
    -0.59
     ErrIntOverflow
    -0.58
    addCriterion
    -0.58
     برانيه
    -0.57
    expandindo
    -0.57
    testng
    -0.57
    POSITIVE LOGITS
     majority
    1.71
    majority
    1.54
    Majority
    1.34
     Majority
    1.29
     mayoría
    1.27
     majorité
    1.20
     maioria
    1.13
     Mehrheit
    1.11
     большин
    1.08
     большинство
    1.02
    Act Density 0.291%

    No Known Activations