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

    Neuronpedia

    INDEX
    Explanations

    terms related to computing and parallel processing in advanced systems

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

    Terms related to computer processing units

    np_acts-logits-general · gemini-2.0-flash

    CPU and performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.52
     puissiez
    -0.49
    éez
    -0.48
    RetentionPolicy
    -0.48
    Continuity
    -0.47
    ergies
    -0.47
    Sire
    -0.46
     fathoms
    -0.46
     sogni
    -0.46
     foncé
    -0.45
    POSITIVE LOGITS
     CPU
    1.49
     processor
    1.28
    CPU
    1.24
     computing
    1.20
     performance
    1.20
     GPU
    1.19
     cpu
    1.17
     compute
    1.12
     computational
    1.11
     Processor
    1.09
    Act Density 0.965%

    No Known Activations