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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting indicators in text

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

    user input follows `<start_of_turn>`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bezeichneter
    -0.52
     تضيفلها
    -0.45
     CanadaChoose
    -0.36
    sizeCache
    -0.36
    HasIndex
    -0.35
    GeoNames
    -0.35
    penup
    -0.33
    Garantía
    -0.33
    waitKey
    -0.33
     TextInputType
    -0.32
    POSITIVE LOGITS
    setVerticalGroup
    0.68
     dieſes
    0.66
    [@BOS@]
    0.63
    <unused14>
    0.62
    <unused43>
    0.61
    <unused23>
    0.61
    <unused52>
    0.61
    <unused74>
    0.61
    <pad>
    0.61
    <unused8>
    0.61
    Act Density 0.000%

    No Known Activations