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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology and references to research publications

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

    Formatting conventions for citations and URLs

    np_acts-logits-general · gemini-2.0-flash

    numbers, punctuation, and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =";
    -0.45
    čnih
    -0.45
     geral
    -0.43
    Добрый
    -0.43
     webinar
    -0.42
    цездатний
    -0.42
     Webinar
    -0.41
    inerja
    -0.40
    Review
    -0.40
    わ
    -0.40
    POSITIVE LOGITS
    PhysRevLett
    0.87
    makeConstraints
    0.71
     incomplète
    0.69
     propOrder
    0.68
    AxisAlignment
    0.67
     <",
    0.64
    الدراسه
    0.64
     estekak
    0.63
    CompleteListener
    0.62
    HomeAsUpEnabled
    0.61
    Act Density 0.746%

    No Known Activations