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

    Neuronpedia

    INDEX
    Explanations

    references to file commands and scripts

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

    start of user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.84
    parsedMessage
    -0.79
     kasarigan
    -0.74
    rungsseite
    -0.70
     autorytatywna
    -0.69
    +#+#
    -0.68
     surla
    -0.67
    LLocation
    -0.66
     leaſt
    -0.66
     leſs
    -0.65
    POSITIVE LOGITS
    Sorted
    0.32
    Python
    0.31
    ',
    0.30
     -*-
    0.29
    mbox
    0.29
     Bucure
    0.29
    德里
    0.28
     dormitórios
    0.28
    Bro
    0.28
     дели
    0.28
    Act Density 0.002%

    No Known Activations