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

    Neuronpedia

    INDEX
    Explanations

    the presence of system output statements and periods

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

    System.out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.79
     ddelweddau
    -0.78
    parsedMessage
    -0.76
    躇
    -0.71
     queſta
    -0.71
    transQ
    -0.69
     OMITBAD
    -0.69
    ésultats
    -0.69
     パンチラ
    -0.67
    ſelben
    -0.67
    POSITIVE LOGITS
    console
    0.54
    mathbb
    0.50
    mathcal
    0.41
    S
    0.39
    Bbb
    0.38
    saraba
    0.36
    stdio
    0.35
    ↵
    0.35
    ::
    0.35
    //.
    0.34
    Act Density 0.002%

    No Known Activations