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

    Neuronpedia

    INDEX
    Explanations

    occurrences of quotation marks or dialogue indicators in the text

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

    start of turn user input

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

    the start of a spoken utterance — an opening quotation mark or the beginning of direct dialogue.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.52
     piatta
    -0.50
    MigrationBuilder
    -0.50
    }`).
    -0.47
     thereafter
    -0.45
    Географија
    -0.45
    Filmografia
    -0.45
     HasFactory
    -0.44
     vägen
    -0.44
    ":[{
    -0.43
    POSITIVE LOGITS
     تكبرها
    0.43
    0.40
    Geplaatst
    0.37
    '
    0.37
    췄
    0.37
    يميديا
    0.36
    Ừ
    0.36
    I
    0.35
     Administrativna
    0.35
    Географиясе
    0.35
    Act Density 0.006%

    No Known Activations