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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistical references

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

    Tokens appearing before bracketed numbers

    np_acts-logits-general · gemini-2.0-flash

    citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.56
    :✨
    -0.45
     endfor
    -0.45
    DoubleQuotes
    -0.44
     Wikimedijinoj
    -0.44
    __":
    -0.42
    +#+#
    -0.41
    PyExc
    -0.41
    Rüyada
    -0.41
    外部リンク
    -0.40
    POSITIVE LOGITS
    期刊论文
    0.53
    mogat
    0.43
     oculto
    0.43
    routeProvider
    0.41
     marcado
    0.39
     anunciar
    0.38
     simplifié
    0.38
     destacado
    0.38
    exitRule
    0.36
     betweenstory
    0.36
    Act Density 0.914%

    No Known Activations