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

    Neuronpedia

    INDEX
    Explanations

    references to individuals in positions of authority or notable roles

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

    Occupations or roles

    np_acts-logits-general · gemini-2.0-flash

    profession followed by name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     their
    -0.70
     ')[
    -0.69
    ]]);
    -0.67
    //});
    -0.66
     two
    -0.65
    出版年
    -0.65
    })));
    -0.65
    "]));
    -0.64
     our
    -0.64
     various
    -0.64
    POSITIVE LOGITS
     extraordinaire
    0.90
    ,
    0.86
    /
    0.85
    -
    0.75
     –
    0.68
     iaitu
    0.67
    —
    0.67
    们
    0.63
    們
    0.62
     who
    0.60
    Act Density 0.273%

    No Known Activations