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

    Neuronpedia

    INDEX
    Explanations

    code structures involving conditional statements and function definitions

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

    Code and mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    existing or previous states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.57
    EDEFAULT
    -0.54
     فريبيس
    -0.52
    RTEE
    -0.46
    forName
    -0.46
     ویکی‌آمباردا
    -0.45
    enumii
    -0.42
    invokeLater
    -0.40
    autique
    -0.40
    .*")]
    -0.40
    POSITIVE LOGITS
     existing
    0.71
     already
    0.68
    existing
    0.67
     previously
    0.65
    Existing
    0.64
     Existing
    0.64
    already
    0.64
     previous
    0.59
    previously
    0.57
     preexisting
    0.57
    Act Density 0.276%

    No Known Activations