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

    Neuronpedia

    INDEX
    Explanations

    proper names and notable figures in various contexts

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

    Unusual surnames or names

    np_acts-logits-general · gemini-2.0-flash

    names or surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.68
    __]
    -0.66
     ddelweddau
    -0.65
    $.}
    -0.65
     للاسماء
    -0.65
    heast
    -0.64
    gitte
    -0.61
     kasarigan
    -0.61
    انيف
    -0.61
    ]>=
    -0.60
    POSITIVE LOGITS
    xase
    0.57
    ніципалі
    0.50
     ſhould
    0.50
     himſelf
    0.49
     herself
    0.49
    riezmann
    0.48
     bershka
    0.48
     himself
    0.48
     myſelf
    0.46
    XmlEnum
    0.46
    Act Density 0.521%

    No Known Activations