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

    Neuronpedia

    INDEX
    Explanations

    references to characters or significant elements within narratives or stories

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

    section references (sec:)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.38
    раздо
    -0.37
     Zentral
    -0.37
    ambién
    -0.34
     merci
    -0.34
     unsuitable
    -0.33
    znac
    -0.32
     comen
    -0.32
     mắc
    -0.31
     geschikt
    -0.31
    POSITIVE LOGITS
     للاسماء
    0.80
    ंदीखरीदारी
    0.60
    :✨
    0.60
    таратура
    0.57
    PerformLayout
    0.56
     esternos
    0.55
     ***!
    0.52
     transférez
    0.50
    出版年
    0.50
    ⓧ
    0.50
    Act Density 0.024%

    No Known Activations