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

    Neuronpedia

    INDEX
    Explanations

    occurrences of plugin-related syntax in code or configuration documents

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

    plugins, user, weekend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     euth
    -0.46
    lanniksi
    -0.42
    igshid
    -0.41
    Transkript
    -0.41
    arpa
    -0.40
    doGet
    -0.39
     TType
    -0.38
     Вікіпе
    -0.38
     transcribed
    -0.38
    ệu
    -0.38
    POSITIVE LOGITS
    plugins
    1.02
     plugins
    0.97
     Plugins
    0.88
    Plugins
    0.82
     plugin
    0.75
     Plugin
    0.66
    插件
    0.66
    plugin
    0.65
    Plugin
    0.63
    InjectAttribute
    0.54
    Act Density 0.005%

    No Known Activations