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

    Neuronpedia

    INDEX
    Explanations

    HTML formatting and code snippets, including tags, buttons, and navigation elements.

    oai_token-act-pair · gemini-2.0-flash

    HTML/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.63
    parsedMessage
    -0.59
     alphabetical
    -0.58
     broadest
    -0.58
     shortest
    -0.58
     Gorb
    -0.56
    carnation
    -0.55
    DoubleQuotes
    -0.55
     ASR
    -0.54
     Arsen
    -0.54
    POSITIVE LOGITS
     And
    0.49
    EndGlobalSection
    0.48
    /
    0.47
    +#+#
    0.45
     It
    0.44
    "}";
    0.43
     cebola
    0.43
    as
    0.42
    findpost
    0.42
    {/
    0.42
    Act Density 2.171%

    No Known Activations