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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to experimental setups and measurements

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

    Equipment or methods used in experiments

    np_acts-logits-general · gemini-2.0-flash

    experimental setups and equipment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.33
    ècie
    -0.31
     terão
    -0.30
     répartition
    -0.30
    orghe
    -0.29
    RenderAtEndOf
    -0.28
     sár
    -0.27
     bacio
    -0.27
     bersi
    -0.27
    cipitation
    -0.27
    POSITIVE LOGITS
    :✨
    0.62
     experimenter
    0.56
     laboratory
    0.56
    kesha
    0.56
    testers
    0.54
     tester
    0.53
     Laboratory
    0.52
     researcher
    0.51
    IsMutable
    0.51
    laboratory
    0.50
    Act Density 0.784%

    No Known Activations