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

    Neuronpedia

    INDEX
    Explanations

    references to speed

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

    speed and its control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    argout
    -0.48
     [*]
    -0.44
     four
    -0.42
     Boch
    -0.40
     Malle
    -0.39
     Chua
    -0.39
     vier
    -0.39
     Cohn
    -0.38
     Bret
    -0.38
    [@"
    -0.37
    POSITIVE LOGITS
     speed
    1.91
    Speed
    1.75
    speed
    1.74
     Speed
    1.69
     SPEED
    1.62
     speeds
    1.55
    SPEED
    1.54
     Speeds
    1.42
    peed
    1.41
     velocidad
    1.27
    Act Density 0.012%

    No Known Activations