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

    Neuronpedia

    INDEX
    Explanations

    specific numerical data and punctuation used in structured formats or lists

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

    which is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.62
    帖最后由
    -0.60
    تقاوى
    -0.59
     Administrativna
    -0.58
     ویکی‌پدیا
    -0.57
    enterOuterAlt
    -0.55
     gyhoeddwyd
    -0.52
    annica
    -0.50
     contextLoads
    -0.50
     patr
    -0.49
    POSITIVE LOGITS
    :✨
    0.45
    <bos>
    0.39
     AssemblyTitle
    0.37
     personalities
    0.36
    ➽
    0.35
    はじめに
    0.34
    ✨:
    0.34
     /\.
    0.34
     taas
    0.34
     hires
    0.34
    Act Density 0.018%

    No Known Activations