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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to programming and data processing

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

    statistical moments and ranks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ah
    -0.41
    τω
    -0.40
    ASYNC
    -0.40
    SS
    -0.39
     SS
    -0.38
    有
    -0.38
    avg
    -0.37
    Blue
    -0.37
    Governor
    -0.37
     Gray
    -0.37
    POSITIVE LOGITS
    +#+#
    0.79
    تقاوى
    0.65
     المعيارى
    0.65
    Билгалдахарш
    0.64
    SequentialGroup
    0.57
     препратки
    0.57
    :✨
    0.56
    GTCX
    0.56
     kasarigan
    0.55
    TemporalType
    0.55
    Act Density 0.011%

    No Known Activations