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

    Neuronpedia

    INDEX
    Explanations

    terms related to processing efficiency and throughput in technical contexts

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

    throughput

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seal
    -0.40
    resaid
    -0.39
     musuh
    -0.37
     fausse
    -0.37
     digitais
    -0.36
     vacuna
    -0.35
     label
    -0.35
    */].
    -0.35
     vœ
    -0.35
     virgin
    -0.34
    POSITIVE LOGITS
     throughput
    2.11
    throughput
    1.95
    Throughput
    1.81
    through
    0.98
     THROUGH
    0.93
     Through
    0.91
    THROUGH
    0.89
    Through
    0.88
     through
    0.83
    Thru
    0.81
    Act Density 0.005%

    No Known Activations