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

    Neuronpedia

    INDEX
    Explanations

    occupations and professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lest
    0.49
     mycop
    0.47
     diapers
    0.47
     somewhat
    0.46
     subsidies
    0.46
    millimeters
    0.46
     processes
    0.46
     prescriptions
    0.45
    _
    0.45
     subsections
    0.45
    POSITIVE LOGITS
     delight
    0.50
     타
    0.48
     최고의
    0.47
     அற்புதமான
    0.46
     ആയ
    0.46
     その他
    0.46
     بيان
    0.46
    בּ
    0.45
     ಮೊದಲ
    0.45
     гід
    0.45
    Act Density 0.003%

    No Known Activations