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

    Neuronpedia

    INDEX
    Explanations

    comments and documentation in code

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

    symbols and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wikipagina
    -0.52
    <blockquote>
    -0.52
    GET
    -0.52
     Administrativna
    -0.52
    IBOutlet
    -0.50
    devise
    -0.48
    get
    -0.47
    <b>
    -0.47
    bukkit
    -0.46
    igay
    -0.46
    POSITIVE LOGITS
    //
    1.83
    #
    1.14
    %
    1.00
     //
    0.94
    ##
    0.79
    ///
    0.75
    //!
    0.57
     *
    0.56
    ſelf
    0.54
    municipi
    0.54
    Act Density 0.009%

    No Known Activations