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

    Neuronpedia

    INDEX
    Explanations

    references to research methodologies and studies

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

    Citations or references (e.g. [@CR21])

    np_acts-logits-general · gemini-2.0-flash

    references and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.49
     استنادى
    -0.45
    #
    -0.43
     Bewußt
    -0.43
     Einfluß
    -0.40
     }{@
    -0.40
    Havolalar
    -0.39
    twimg
    -0.39
    LayoutStyle
    -0.38
     arşivlendi
    -0.37
    POSITIVE LOGITS
    Personendaten
    0.54
    enderror
    0.52
    leski
    0.47
    Grav
    0.43
     sfera
    0.42
    uvwxyz
    0.42
    PropTypes
    0.42
    ITECH
    0.42
    Earl
    0.42
     Verder
    0.42
    Act Density 0.557%

    No Known Activations