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

    Neuronpedia

    INDEX
    Explanations

    source code formatting and syntax, specifically looking for indentation and patterns in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    JSON-like structures

    np_token-act-pair-logits · gpt-4o-mini

    curly brace

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.95
     auffi
    -0.94
     FetchType
    -0.85
    ]--;
    -0.85
    aarrggbb
    -0.82
     Jefus
    -0.82
     للمعارف
    -0.82
     wikipagina
    -0.82
     ModelExpression
    -0.81
     ainfi
    -0.81
    POSITIVE LOGITS
     {
    0.90
    {
    0.78
     {}
    0.59
    {~
    0.57
    {}
    0.56
     {'
    0.56
    >{
    0.55
     {?
    0.53
     {(
    0.53
    nting
    0.53
    Act Density 0.807%

    No Known Activations