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

    Neuronpedia

    INDEX
    Explanations

    paths or directories used in a file structure

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

    Relative paths indicating file locations

    np_acts-logits-general · gemini-2.0-flash

    file paths and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -1.01
     ―――――
    -0.90
     وتسجيلات
    -0.90
    verwijspagina
    -0.90
     ་་
    -0.88
     AssemblyTitle
    -0.87
    SourceChecksum
    -0.87
    styleType
    -0.87
     AssemblyVersion
    -0.86
    GEBURTSDATUM
    -0.86
    POSITIVE LOGITS
    <eos>
    0.55
     
    0.45
    apt
    0.45
    =[];
    0.45
     su
    0.44
     whole
    0.43
     "..\..\..\
    0.43
     entire
    0.43
     exemples
    0.42
     esses
    0.41
    Act Density 0.396%

    No Known Activations