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

    Neuronpedia

    INDEX
    Explanations

    references to grandmothers or maternal figures

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

    grandmother, grandma, abuela

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ares
    -0.54
    sector
    -0.52
    flap
    -0.50
    PerformLayout
    -0.49
    bufio
    -0.49
    RenderAtEndOf
    -0.49
    situ
    -0.49
     Cyril
    -0.48
     Doi
    -0.48
     Sector
    -0.48
    POSITIVE LOGITS
     grandmother
    1.75
     Grandmother
    1.49
    grandmother
    1.42
     grandma
    1.06
     Grandma
    1.05
    Grandma
    1.05
     abuela
    0.96
     grandparents
    0.82
    mothers
    0.81
    祖母
    0.73
    Act Density 0.005%

    No Known Activations