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

    Neuronpedia

    INDEX
    Explanations

    consistent structure or formatting in the data

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

    scientific and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.51
     Traditional
    -0.45
    IContainer
    -0.44
     Cron
    -0.42
     للمعارف
    -0.42
     Brin
    -0.41
     Cars
    -0.41
     cliquez
    -0.40
    riff
    -0.40
     VEH
    -0.40
    POSITIVE LOGITS
    __':
    0.51
     nahilalakip
    0.49
    __":
    0.48
    UnusedPrivate
    0.47
    __':
    0.45
     ويكيميديا
    0.42
     betweenstory
    0.41
     Svizzera
    0.41
    apunov
    0.41
     вікісторінку
    0.39
    Act Density 0.039%

    No Known Activations