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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and function definitions in code

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

    embedded code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tampere
    -0.25
     colaboración
    -0.24
     Konsequ
    -0.23
    </em>
    -0.23
     against
    -0.23
     Vorge
    -0.23
    ↵↵
    -0.23
    un
    -0.23
     wybor
    -0.23
     saja
    -0.23
    POSITIVE LOGITS
     AssemblyCulture
    0.85
     transfieras
    0.82
     مرئيه
    0.81
    تقاوى
    0.81
     kaarangay
    0.79
     autorytatywna
    0.76
     ویکی‌پدی
    0.76
    RegistryLite
    0.76
     незавершена
    0.75
     Мексичка
    0.75
    Act Density 0.061%

    No Known Activations