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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships, particularly those involving grandmothers and grandchildren

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

    Family relationships (grandparents, grandson, uncle)

    np_acts-logits-general · gemini-2.0-flash

    grandfamily members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    providedIn
    -0.79
    angliski
    -0.79
    Akt
    -0.72
    DataMember
    -0.72
    hakti
    -0.71
     Hati
    -0.71
     SafeMath
    -0.70
    enumi
    -0.70
    ंदीखरीदारी
    -0.68
     communiquez
    -0.66
    POSITIVE LOGITS
    Grandpa
    0.92
     grandparents
    0.91
     Grandpa
    0.90
     GRAND
    0.84
    Grandma
    0.83
     Grandfather
    0.82
     grandpa
    0.82
     grandfather
    0.81
     grandma
    0.81
    Grand
    0.79
    Act Density 0.089%

    No Known Activations