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

    Neuronpedia

    INDEX
    Explanations

    references to variable names and method parameters in code

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

    references to prompt-related elements in programming contexts

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

    programming and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    []
    -0.53
    InstanceOf
    -0.51
     Zahl
    -0.51
     [];
    -0.49
    ঔ
    -0.49
    bole
    -0.47
    ortive
    -0.46
    styleable
    -0.45
    ([]);
    -0.45
    ()))
    -0.44
    POSITIVE LOGITS
    Personendaten
    0.92
    ChromeDriver
    0.86
    AndEndTag
    0.81
    astéroïdes
    0.80
    IRQn
    0.77
     مشين
    0.76
    DotNetBar
    0.74
     betweenstory
    0.73
     AssemblyVersion
    0.73
    WebServlet
    0.73
    Act Density 0.077%

    No Known Activations