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

    Neuronpedia

    INDEX
    Explanations

    reference to notable individuals and their achievements or roles

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

    biographies and proper names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.54
    Попис
    -0.48
    Obrázky
    -0.39
    Théâtre
    -0.39
    ⎨
    -0.38
     réaliste
    -0.38
     Щ
    -0.36
    isdir
    -0.36
     ***!
    -0.36
     שוליים
    -0.35
    POSITIVE LOGITS
     himself
    0.57
    참고
    0.57
    himself
    0.50
    sonaro
    0.49
    homonymie
    0.47
    onaceous
    0.47
     Filho
    0.47
     Obrador
    0.47
     Paglinawan
    0.46
    clusal
    0.45
    Act Density 0.082%

    No Known Activations