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

    Neuronpedia

    INDEX
    Explanations

    programming and file handling concepts

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

    Filename, command, URL, or value processing

    np_acts-logits-general · gemini-2.0-flash

    common variable names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    بالإنجليزية
    -0.57
     gili
    -0.54
    WebServlet
    -0.50
    kamers
    -0.49
     FormData
    -0.48
    equivalent
    -0.47
    parseDouble
    -0.47
     ốc
    -0.46
     Sequences
    -0.46
     لقد
    -0.46
    POSITIVE LOGITS
    openqa
    0.76
     snippetHide
    0.75
     EconPapers
    0.74
     InputDecoration
    0.71
    apimachinery
    0.71
    aarrggbb
    0.69
    MemoryWarning
    0.68
     تضيفلها
    0.63
    LayoutStyle
    0.63
     viewDidLoad
    0.63
    Act Density 0.208%

    No Known Activations