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

    Neuronpedia

    INDEX
    Explanations

    references to immigration and citizenship statuses

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

    Country of origin or citizenship

    np_acts-logits-general · gemini-2.0-flash

    origin and nationality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TintMode
    -0.75
    -0.68
    UnusedPrivate
    -0.62
    expandindo
    -0.61
    헌
    -0.61
     ModelExpression
    -0.59
    findpost
    -0.58
     betweenstory
    -0.57
    OrNil
    -0.57
     correctes
    -0.56
    POSITIVE LOGITS
     hails
    1.61
     origin
    1.59
     originate
    1.57
     originating
    1.56
     originated
    1.53
     originates
    1.52
     originaire
    1.43
    origin
    1.41
     native
    1.40
     Origin
    1.37
    Act Density 0.398%

    No Known Activations