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

    Neuronpedia

    INDEX
    Explanations

    elements of web URLs

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

    URLs after a period

    np_acts-logits-general · gemini-2.0-flash

    websites and domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.54
    expiresIn
    -0.51
    .
    -0.46
     E
    -0.46
     here
    -0.45
     an
    -0.43
    ↵↵
    -0.43
     Ra
    -0.43
    2
    -0.41
    Sincerely
    -0.40
    POSITIVE LOGITS
    ########.
    0.95
    ValueStyle
    0.89
     OFDb
    0.87
    +#+#
    0.83
     Wikimedijinoj
    0.82
     ujednoznacz
    0.80
     يتيمه
    0.79
     ***!
    0.79
     quæ
    0.79
    Datuak
    0.79
    Act Density 0.122%

    No Known Activations