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

    Neuronpedia

    INDEX
    Explanations

    references to individuals' names and their familial connections

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

    "Joe" or "Joseph" followed by a last name

    np_acts-logits-general · gemini-2.0-flash

    names like Joe and Joseph

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ffler
    -0.58
     resourceCulture
    -0.50
    AsStream
    -0.47
     diet
    -0.47
     voice
    -0.46
    Alike
    -0.46
    atchi
    -0.46
    diez
    -0.46
    stam
    -0.45
     patch
    -0.45
    POSITIVE LOGITS
     beginnetje
    0.72
     jsPsych
    0.63
    COUVER
    0.63
     ſhe
    0.59
    Jeografia
    0.59
    ftagPool
    0.59
    SharedDtor
    0.59
     Cæsar
    0.58
     autorytatywna
    0.56
    utilisons
    0.56
    Act Density 0.292%

    No Known Activations