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

    Neuronpedia

    INDEX
    Explanations

    mentions of measurement and data analysis techniques

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

    acronyms and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    printStackTrace
    -0.44
     tả
    -0.43
     за
    -0.42
     prohibido
    -0.42
     aço
    -0.40
    abet
    -0.40
    field
    -0.39
    lear
    -0.39
    tuce
    -0.39
    </h3>
    -0.39
    POSITIVE LOGITS
     MM
    2.31
    MM
    2.17
     mm
    1.61
    mm
    1.41
     Mm
    1.31
     MMS
    1.30
     MMR
    1.26
    Mm
    1.23
     MMC
    1.23
     MMM
    1.21
    Act Density 0.021%

    No Known Activations