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

    Neuronpedia

    INDEX
    Explanations

    references to family names and genealogy, specifically focusing on the Sanders and Saunders surnames

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

    Sanders family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.80
    <unused41>
    -0.80
    [@BOS@]
    -0.80
    <unused8>
    -0.79
     deſſen
    -0.79
    <unused17>
    -0.79
    <unused68>
    -0.79
    <unused42>
    -0.79
    <unused14>
    -0.79
    <unused16>
    -0.79
    POSITIVE LOGITS
     family
    0.40
     families
    0.30
    family
    0.28
     Family
    0.28
     keluarganya
    0.27
     famílias
    0.26
     others
    0.25
     keluarga
    0.24
     familles
    0.23
     csalá
    0.23
    Act Density 0.029%

    No Known Activations