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

    Neuronpedia

    INDEX
    Explanations

    technical terms and acronyms related to system architecture and processing methods

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

    detection: ELF, CFS, PI, DR, ICE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    flowered
    -0.38
    ContainsKey
    -0.35
    Universidad
    -0.34
     Michoacán
    -0.34
    bot
    -0.34
     Sünde
    -0.33
     surprised
    -0.33
    (©
    -0.33
    itzender
    -0.33
     compiled
    -0.33
    POSITIVE LOGITS
     فريبيس
    0.58
    IndentedString
    0.56
    icordia
    0.55
     wikipagina
    0.54
    transQ
    0.51
     aikaa
    0.51
    migrationBuilder
    0.50
    URLException
    0.50
    Билгалдахарш
    0.49
     ProtoMessage
    0.48
    Act Density 1.242%

    No Known Activations