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

    Neuronpedia

    INDEX
    Explanations

    terms related to debugging and development processes

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

    Software development and debugging

    np_acts-logits-general · gemini-2.0-flash

    local development and debugging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.54
    ьаж
    -0.50
     autorytatywna
    -0.47
     allAfrica
    -0.47
    -0.45
    Jîn
    -0.43
     Paglinawan
    -0.42
    ########.
    -0.42
    RenderAtEndOf
    -0.41
    ArgsConstructor
    -0.40
    POSITIVE LOGITS
     везе
    0.51
    devServer
    0.45
    TargetException
    0.42
     cómodo
    0.40
     UnityEditor
    0.39
    atoga
    0.39
     memudahkan
    0.38
     Wikimedijinoj
    0.38
    tangentMode
    0.37
    调试
    0.37
    Act Density 0.495%

    No Known Activations