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

    Neuronpedia

    INDEX
    Explanations

    coding syntax and structure elements

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

    closing braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.88
     betweenstory
    -0.84
     kasarigan
    -0.79
     ویکی‌پدی
    -0.77
     propOrder
    -0.76
     defaultstate
    -0.75
     iprot
    -0.75
    devamını
    -0.74
    parsedMessage
    -0.74
     فريبيس
    -0.73
    POSITIVE LOGITS
    .
    0.40
     and
    0.40
    ↵↵
    0.38
     if
    0.36
     while
    0.35
     for
    0.35
     when
    0.33
     because
    0.32
     although
    0.32
    <eos>
    0.31
    Act Density 0.004%

    No Known Activations