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

    Neuronpedia

    INDEX
    Explanations

    specific roles or types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    daughters
    1.09
     ছেলেদের
    1.04
     मंत्रियों
    1.01
     meninas
    1.01
    孩子们
    1.01
    killers
    1.01
     بنات
    0.99
     শিক্ষকদের
    0.98
    clientes
    0.98
    mothers
    0.97
    POSITIVE LOGITS
     person
    1.50
     member
    1.37
     researcher
    1.27
     colleague
    1.17
     devotee
    1.13
     attendee
    1.12
     participant
    1.09
     scientist
    1.08
     strategist
    1.08
     practitioner
    1.08
    Act Density 0.754%

    No Known Activations