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

    Neuronpedia

    INDEX
    Explanations

    references to scientific articles and their citation formats

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

    academic references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.66
    ſelf
    -0.61
    +#+#
    -0.58
    GEBURTSDATUM
    -0.57
    nodoc
    -0.53
     ویکی‌پدی
    -0.51
     defaultstate
    -0.49
    awtextra
    -0.48
    complexContent
    -0.47
     ſte
    -0.47
    POSITIVE LOGITS
     nahilalakip
    0.39
    cetto
    0.35
    KommentareTeilen
    0.35
     repeal
    0.34
     vist
    0.34
     jazz
    0.34
     Steam
    0.33
    enskap
    0.33
     ticket
    0.33
    Sklici
    0.33
    Act Density 0.029%

    No Known Activations