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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships and lineage

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

    Family relationships, especially grandparents and ancestors

    np_acts-logits-general · gemini-2.0-flash

    grand parental terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.82
    بوابة
    -0.79
     otomatig
    -0.79
     NSCoder
    -0.77
    GEBURTSDATUM
    -0.74
    ]--;
    -0.71
     daughter
    -0.71
    Portail
    -0.69
     nahilalakip
    -0.68
     Daughter
    -0.68
    POSITIVE LOGITS
     grand
    1.62
    grand
    1.60
    Grand
    1.56
     Grand
    1.52
     GRAND
    1.49
    GRAND
    1.45
     grandparents
    1.31
     grandfather
    1.30
     grandmother
    1.21
     grandpa
    1.18
    Act Density 0.150%

    No Known Activations