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

    Neuronpedia

    INDEX
    Explanations

    elements of emotional complexity and nuanced characterization in narratives

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

    adjective describing negative or descriptive quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gwaran
    -0.31
     Geschichten
    -0.31
     seguintes
    -0.30
     levier
    -0.29
    kwür
    -0.28
     przedsiębior
    -0.28
     Abweich
    -0.27
     acabamento
    -0.27
     następu
    -0.26
     gás
    -0.26
    POSITIVE LOGITS
    دانشنامهٔ
    0.67
    falgar
    0.66
     становника
    0.66
     gyhoeddwyd
    0.66
     cherchés
    0.64
     SafeMath
    0.63
     nahilalakip
    0.62
    Hentet
    0.62
    awtextra
    0.61
     oprot
    0.61
    Act Density 0.198%

    No Known Activations