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

    Neuronpedia

    INDEX
    Explanations

    references to specific file handling and input/output exceptions in programming

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

    Code, scripts, and programming-related text

    np_acts-logits-general · gemini-2.0-flash

    code snippets and foreign characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.64
    tende
    -0.57
     open
    -0.56
    *>(
    -0.55
     per
    -0.52
     brand
    -0.51
     so
    -0.51
     Central
    -0.50
    BuilderFactory
    -0.49
     dAtA
    -0.49
    POSITIVE LOGITS
    RectangleBorder
    0.80
     ujednoznacz
    0.78
     فريبيس
    0.78
     snippetHide
    0.75
    stdc
    0.70
    ;
    0.69
     متعلقه
    0.69
     дописавши
    0.69
    IntoConstraints
    0.67
    DoubleQuotes
    0.66
    Act Density 0.029%

    No Known Activations