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

    Neuronpedia

    INDEX
    Explanations

    ity

    np_max-act · gemini-2.0-flash

    The neuron detects descriptive, often multi-syllabic adjectives and abstract nouns (e.g. “uniformity,” “conservative,” “aggressive,” “detached,” “realism”) that characterize qualities or styles.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     температуры
    -0.06
     dum
    -0.06
    heritance
    -0.06
     wool
    -0.06
    κτη
    -0.06
    .minute
    -0.06
    /*!↵
    -0.06
     dataSource
    -0.06
    GetObject
    -0.06
     datePicker
    -0.06
    POSITIVE LOGITS
     Arizona
    0.07
    Billing
    0.07
    needed
    0.06
    ское
    0.06
    minor
    0.06
    @register
    0.06
     pleaded
    0.06
     اولیه
    0.06
    dration
    0.06
     DISABLE
    0.06
    Act Density 0.142%

    No Known Activations