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

    Neuronpedia

    INDEX
    Explanations

    specially formatted numeric values and punctuation in a structured context

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

    Numbers within legal citations

    np_acts-logits-general · gemini-2.0-flash

    legal citations containing numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GTCX
    -0.43
    #+#
    -0.42
     سوق
    -0.38
    sizeCache
    -0.36
     Powder
    -0.33
     Sleeper
    -0.33
    :+:
    -0.32
    msgSender
    -0.32
    Coffee
    -0.31
     bakar
    -0.31
    POSITIVE LOGITS
     ब्रेकडाउन
    0.53
     lenker
    0.52
     NSCoder
    0.48
    Manbalar
    0.47
     kasarigan
    0.47
     становника
    0.45
     odkazy
    0.44
    🖨
    0.43
     stanovnika
    0.42
    errHandler
    0.41
    Act Density 0.582%

    No Known Activations