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

    Neuronpedia

    INDEX
    Explanations

    structured programming elements and code syntax

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

    Code blocks containing "return" or "if"

    np_acts-logits-general · gemini-2.0-flash

    conditional logic and error handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setupUi
    -0.78
     Derfor
    -0.75
     وتسجيلات
    -0.67
    nehå
    -0.65
     døde
    -0.59
     bolig
    -0.59
    atsby
    -0.59
    føl
    -0.58
    nolia
    -0.58
     dibuka
    -0.57
    POSITIVE LOGITS
    if
    1.00
    {
    0.78
    +#+#
    0.66
    return
    0.61
    ((
    0.59
    //
    0.56
    switch
    0.55
    try
    0.55
    {
    0.54
    ())))
    0.53
    Act Density 0.042%

    No Known Activations