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

    Neuronpedia

    INDEX
    Explanations

    closing braces and related syntax in code

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

    Code block closures

    np_acts-logits-general · gemini-2.0-flash

    else or else if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.93
     referenties
    -0.82
     שוליים
    -0.81
     חיצוניים
    -0.77
     Bourgoin
    -0.71
    ✭✭
    -0.70
    kháu
    -0.66
    Hentet
    -0.66
    IUrlHelper
    -0.65
    TagMode
    -0.65
    POSITIVE LOGITS
     catch
    0.90
    catch
    0.75
     while
    0.73
     else
    0.66
    ),
    0.65
    ↵
    0.62
    while
    0.61
    ↵↵
    0.59
    else
    0.59
    );
    0.57
    Act Density 0.128%

    No Known Activations