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

    Neuronpedia

    INDEX
    Explanations

    names and references to individuals and entities

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

    names

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects personal names, bylines, usernames, and email/handle tokens (author/identity markers).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ]")]
    -0.52
    paravant
    -0.40
    TheReal
    -0.36
     SimpleName
    -0.36
     fú
    -0.36
    InThe
    -0.35
     alent
    -0.33
     Slovensku
    -0.33
     phare
    -0.32
    xFFFFFF
    -0.32
    POSITIVE LOGITS
    endphp
    0.70
    ThroughAttribute
    0.67
     okuyayım
    0.67
    aarrggbb
    0.66
    transQ
    0.65
     تانيه
    0.63
     resourceCulture
    0.63
     مشين
    0.62
     @"/
    0.61
     rhestr
    0.61
    Act Density 1.045%

    No Known Activations