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

    Neuronpedia

    INDEX
    Explanations

    familial relationships, especially references to uncles and aunts

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

    uncle and aunt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SafeMath
    -0.50
     AssemblyCulture
    -0.45
    妙
    -0.43
    уда
    -0.42
    الحياه
    -0.42
     >>=
    -0.42
     Nade
    -0.42
    remarks
    -0.42
     Kinders
    -0.42
    mathop
    -0.41
    POSITIVE LOGITS
     uncles
    1.59
     aunts
    1.37
     uncle
    1.13
     aunt
    0.85
    uncle
    0.82
     grandfather
    0.73
     grandparents
    0.69
     tío
    0.66
     cousins
    0.65
    Uncle
    0.65
    Act Density 0.002%

    No Known Activations