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

    Neuronpedia

    INDEX
    Explanations

    code that defines the main method in Java

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

    "String" or "int" followed by "args"

    np_acts-logits-general · gemini-2.0-flash

    main function arguments (`args`, `argv`)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <=",
    -0.89
     utafitiHapana
    -0.83
    Vidite
    -0.69
     متعلقه
    -0.68
     transfieras
    -0.68
    XmlEnum
    -0.68
     estekak
    -0.67
     الرياضيه
    -0.66
     تضيفلها
    -0.65
     يتيمه
    -0.65
    POSITIVE LOGITS
     args
    0.79
    WebControls
    0.65
    args
    0.64
     Args
    0.62
    SpringRunner
    0.62
     Strings
    0.61
    avras
    0.61
    argv
    0.58
     strings
    0.58
    Strings
    0.57
    Act Density 0.084%

    No Known Activations