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

    Neuronpedia

    INDEX
    Explanations

    the beginning of the document or specific sections that indicate a new topic or idea

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

    Code, numbers, and parentheses

    np_acts-logits-general · gemini-2.0-flash

    code syntax and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OFDb
    -0.60
    intios
    -0.53
    verwijspagina
    -0.53
     CiNii
    -0.50
     '{@
    -0.50
    ]--;
    -0.49
    ...",
    -0.48
     Ome
    -0.48
    ...',
    -0.47
    CURS
    -0.47
    POSITIVE LOGITS
    principalTable
    0.84
    <eos>
    0.73
    पया
    0.66
    tadır
    0.66
    rungsseite
    0.64
    Parcelize
    0.62
    unmodifiable
    0.61
    TIMORE
    0.60
     дописавши
    0.59
     ***!
    0.59
    Act Density 0.190%

    No Known Activations