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

    Neuronpedia

    INDEX
    Explanations

    scenarios related to code structure, such as function definitions and variable assignments

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

    Code or data with special characters

    np_acts-logits-general · gemini-2.0-flash

    numbers, code, and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.68
     NSCoder
    -0.66
    Tembelea
    -0.65
    قایناق‌لار
    -0.63
    ProductService
    -0.62
     ProductService
    -0.61
    uesia
    -0.61
     UIApplication
    -0.59
     rospy
    -0.59
    setVerticalGroup
    -0.57
    POSITIVE LOGITS
     CreateTagHelper
    0.60
    ftant
    0.51
    DOCTYPE
    0.50
    ellar
    0.50
    enumii
    0.49
     Grüsse
    0.47
    ghijklmnop
    0.46
    helin
    0.46
     Laughing
    0.46
    ёг
    0.45
    Act Density 0.135%

    No Known Activations