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

    Neuronpedia

    INDEX
    Explanations

    terms related to speed and efficiency in technology

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

    comparative speed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.48
     mergeFrom
    -0.45
     programação
    -0.44
    jface
    -0.40
    MergeFrom
    -0.40
    ApiModelProperty
    -0.40
     تضيفلها
    -0.39
     trụ
    -0.38
     presents
    -0.38
    ynb
    -0.38
    POSITIVE LOGITS
     speed
    1.06
    Speed
    1.02
     SPEED
    0.97
    Speedy
    0.96
     Speed
    0.96
    speed
    0.96
    Faster
    0.95
     speeds
    0.95
    faster
    0.95
     Speedy
    0.94
    Act Density 0.028%

    No Known Activations