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

    Neuronpedia

    INDEX
    Explanations

    references to family members, specifically grandmothers

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

    grandmother and grandma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VYMaps
    -0.50
    plotlib
    -0.49
    MigrationBuilder
    -0.47
    fjspx
    -0.47
    spill
    -0.46
     posX
    -0.46
     appelez
    -0.46
    Hochspringen
    -0.46
    httphttps
    -0.46
     transfieras
    -0.45
    POSITIVE LOGITS
     grandmother
    0.64
     Grandmother
    0.56
    NameInMap
    0.56
    gran
    0.52
     GRAND
    0.50
    👵
    0.49
     gran
    0.49
     GRAN
    0.48
    grandmother
    0.47
     grand
    0.46
    Act Density 0.006%

    No Known Activations