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

    Neuronpedia

    INDEX
    Explanations

    syntax elements and structure in code, particularly focusing on brackets and function calls

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

    Code comments, especially starting with "#"

    np_acts-logits-general · gemini-2.0-flash

    lines starting with #

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     //
    -1.89
    //
    -1.74
    )//
    -1.38
    //"
    -1.21
     //
    -1.21
    //'
    -1.20
    //(
    -1.17
    //{
    -1.14
     {//
    -1.12
    //
    -1.12
    POSITIVE LOGITS
    #
    1.60
     #
    1.49
    #,
    1.18
    #)
    1.03
    #'
    1.01
    ##
    1.00
    #"
    0.96
     #"
    0.96
    #:
    0.96
    #(
    0.93
    Act Density 0.146%

    No Known Activations