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

    Neuronpedia

    INDEX
    Explanations

    references to familial and maternal themes

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

    mother and father

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ensement
    -0.35
    …~
    -0.35
    뀜
    -0.31
    IsPostBack
    -0.30
     lucky
    -0.30
     समीक्षक
    -0.30
     volume
    -0.29
     rolling
    -0.29
    volume
    -0.29
     Paglinawan
    -0.28
    POSITIVE LOGITS
     mothers
    1.08
    Mothers
    1.06
     Mothers
    1.05
    mothers
    1.04
     mother
    1.03
    Mother
    1.00
     fathers
    0.97
     father
    0.96
     moms
    0.96
    mother
    0.95
    Act Density 0.059%

    No Known Activations