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

    Neuronpedia

    INDEX
    Explanations

    references to familial or domestic relationships and care

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

    honorific prefixes お and ご

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    slidesToShow
    -0.57
     estúdio
    -0.54
     Mexique
    -0.54
     santuario
    -0.52
     paisaje
    -0.50
     ciudadana
    -0.50
     Faso
    -0.49
     caucho
    -0.49
     Batalla
    -0.49
     Wikiseite
    -0.49
    POSITIVE LOGITS
    お
    0.78
    のお
    0.71
     お
    0.65
    はお
    0.62
    とお
    0.61
    Gos
    0.61
    御
    0.60
     gos
    0.60
     aDecoder
    0.58
    でお
    0.57
    Act Density 0.004%

    No Known Activations