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

    Neuronpedia

    INDEX
    Explanations

    instances of professional recruitment or job opportunities

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

    Followed by numbers or mathematical symbols

    np_acts-logits-general · gemini-2.0-flash

    sections, numbers, legal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -1.11
    __':
    -1.09
    __":
    -1.07
     ModelExpression
    -0.98
     propOrder
    -0.94
    />";
    -0.94
     كومونز
    -0.93
    featureID
    -0.91
     Wikimedijinoj
    -0.90
    تقاوى
    -0.90
    POSITIVE LOGITS
    .
    0.77
    2
    0.62
    4
    0.61
    5
    0.57
    1
    0.56
    6
    0.56
    3
    0.54
    0
    0.52
    7
    0.51
    8
    0.50
    Act Density 0.103%

    No Known Activations