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

    Neuronpedia

    INDEX
    Explanations

    technical terms and parameters related to thresholds and statistical measures in data processing

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

    setting a threshold value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.44
     Paglinawan
    -0.41
    ReusableCell
    -0.40
    extAlignment
    -0.40
     extérieures
    -0.39
    })*/
    -0.39
    лтемелер
    -0.39
    gameserver
    -0.37
     dren
    -0.36
     breathes
    -0.35
    POSITIVE LOGITS
     threshold
    0.84
     thresholds
    0.69
    threshold
    0.69
     Threshold
    0.66
     critères
    0.65
    Threshold
    0.64
     criteria
    0.63
    THRESHOLD
    0.60
    addCriterion
    0.59
     seuil
    0.58
    Act Density 0.178%

    No Known Activations