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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases related to programming and technical specifications

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

    SELECT occurs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h1>
    -0.57
    　　
    -0.44
    <strong>
    -0.44
    
    -0.43
    The
    -0.43
    <h2>
    -0.42
    第
    -0.42
    [toxicity=0]
    -0.40
    package
    -0.39
    #
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.86
    0.83
    ContentAsync
    0.81
    ArrowToggle
    0.79
     useAppContext
    0.78
     snippetHide
    0.78
     متعلقه
    0.75
    IsContent
    0.74
    httphttps
    0.74
    RegressionTest
    0.72
    Act Density 0.297%

    No Known Activations