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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to racial and ethnic classifications in social contexts

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

    with prefixes and suffixes

    np_acts-logits-general · gemini-2.0-flash

    prefixes or word beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.62
    pyx
    -0.59
    PutMapping
    -0.59
     reç
    -0.56
    Disponible
    -0.56
    medriver
    -0.55
     gratuitement
    -0.55
    printStackTrace
    -0.54
     Zola
    -0.54
     correctes
    -0.53
    POSITIVE LOGITS
     hybrid
    0.64
    出版年
    0.61
     للاسماء
    0.60
     lenker
    0.59
    Hentet
    0.57
     pure
    0.56
     non
    0.56
    ̈́
    0.56
    UnusedPrivate
    0.56
     незавершена
    0.55
    Act Density 0.739%

    No Known Activations