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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and acronyms related to programming and system operations

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

    I followed by uppercase letter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vorteile
    -0.41
    obiettivo
    -0.40
     keselamatan
    -0.39
     dirait
    -0.39
     Beweis
    -0.39
    élimin
    -0.39
    importanza
    -0.38
     Defensa
    -0.38
     Landwir
    -0.38
     muebles
    -0.38
    POSITIVE LOGITS
    IVer
    0.64
     IZ
    0.63
     Normdatei
    0.63
    tershire
    0.62
     ICommand
    0.61
     تضيفلها
    0.60
    IM
    0.60
     IM
    0.59
    IC
    0.59
     IC
    0.58
    Act Density 0.016%

    No Known Activations