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

    Neuronpedia

    INDEX
    Explanations

    articles and quantifiers in the text

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

    the followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects salient content words — topic-bearing or focus words (important nouns, verbs, and adjectives) that carry the main meaning of a sentence.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.54
     Reli
    -0.50
    URLEncoder
    -0.50
     ujednoznacz
    -0.49
     виправивши
    -0.47
     EconPapers
    -0.47
     سب
    -0.46
     jaz
    -0.45
    ViewImports
    -0.45
    zina
    -0.44
    POSITIVE LOGITS
    occuper
    0.50
     JpaRepository
    0.46
     itulah
    0.46
     civilización
    0.46
    Dimensões
    0.45
     információ
    0.45
     étrangère
    0.45
    limiento
    0.44
    SequentialGroup
    0.44
     Económica
    0.44
    Act Density 0.228%

    No Known Activations