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

    Neuronpedia

    INDEX
    Explanations

    specific linguistic patterns or constructs related to characters and names in a narrative context

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

    Chinese names or syllables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.52
     newBuilder
    -0.42
    Abitanti
    -0.41
     мәкал
    -0.41
    værende
    -0.40
    ⓧ
    -0.39
    ","","
    -0.39
    ')],
    -0.38
    ')")
    -0.38
    grà
    -0.37
    POSITIVE LOGITS
    AndEndTag
    0.57
    tvguidetime
    0.52
    Hauptartikel
    0.52
    évaluateur
    0.51
    Dichloropropane
    0.44
     manches
    0.42
    Definición
    0.42
    addContainerGap
    0.41
    ธรรม
    0.41
     impré
    0.41
    Act Density 0.047%

    No Known Activations