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

    Neuronpedia

    INDEX
    Explanations

    the definite article "the" and its context within mathematical or logical queries

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

    what is the term, value, or prime factors

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

    This neuron detects the definite article "the" (the token " the", especially in phrases like "What is the ...").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.85
    parsedMessage
    -0.71
     ویکی‌پدی
    -0.71
     Италијани
    -0.63
    Personendaten
    -0.62
    Autoritní
    -0.59
     незавершена
    -0.59
     Савезне
    -0.58
     AppCompatTheme
    -0.58
     Мексичка
    -0.58
    POSITIVE LOGITS
     zwiſchen
    0.52
     dieſen
    0.51
    Kes
    0.50
     Kes
    0.50
     deſſen
    0.49
     queſto
    0.49
     dieſes
    0.48
    Luong
    0.48
    ⏔
    0.48
    <unused14>
    0.47
    Act Density 0.030%

    No Known Activations