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

    Neuronpedia

    INDEX
    Explanations

    programming terminology and code-related keywords

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

    git diffs and code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تعدى
    -0.38
    therosclerosis
    -0.38
    holder
    -0.36
     extérieure
    -0.35
     exatamente
    -0.34
    embal
    -0.34
     caminhão
    -0.33
     extérieurs
    -0.33
     financière
    -0.33
    folie
    -0.33
    POSITIVE LOGITS
    spi
    3.06
     spi
    1.48
    Spi
    1.21
     Spi
    1.02
    SPI
    0.93
     SPI
    0.82
    ///</
    0.78
    spir
    0.74
     SPIR
    0.72
     ModelRenderer
    0.71
    Act Density 0.001%

    No Known Activations