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

    Neuronpedia

    INDEX
    Explanations

    punctuation and numerical symbols

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

    numbers with commas and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scatt
    -0.37
     connexes
    -0.36
    WithIOException
    -0.36
     fing
    -0.35
    ))]
    -0.35
    ``.
    -0.34
     controver
    -0.33
    __))
    -0.33
     Shooting
    -0.33
    "?
    -0.32
    POSITIVE LOGITS
     kasarigan
    0.61
    readystatechange
    0.55
     يتيمه
    0.52
    sizeCache
    0.52
     felizes
    0.51
     CanadaChoose
    0.51
     nemus
    0.50
     căr
    0.50
     Савезне
    0.49
     Paglinawan
    0.49
    Act Density 0.000%

    No Known Activations