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

    Neuronpedia

    INDEX
    Explanations

    function definitions, specifically those related to initialization

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

    code initializers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Boomer
    -0.38
    MessageTagHelper
    -0.35
    unicaciones
    -0.34
     numerus
    -0.34
    yeb
    -0.33
     boomer
    -0.33
    ,\,\
    -0.32
     Spy
    -0.31
    DataRow
    -0.31
     tslint
    -0.31
    POSITIVE LOGITS
     init
    2.72
     Init
    2.13
    Init
    1.84
     INIT
    1.79
    init
    1.62
     initialization
    1.59
    INIT
    1.55
     initi
    1.54
     Initialization
    1.50
     INITI
    1.44
    Act Density 0.002%

    No Known Activations