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

    Neuronpedia

    INDEX
    Explanations

    terms indicating a decrease or lower level in various contexts

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

    lower followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eventId
    -0.74
    Personensuche
    -0.63
    eventId
    -0.63
     ProtoMessage
    -0.60
     fieldNum
    -0.59
    charCode
    -0.59
    BagLayout
    -0.59
    execSQL
    -0.58
    nanoTime
    -0.58
     MatDialog
    -0.58
    POSITIVE LOGITS
     lower
    2.00
     Lower
    1.80
    Lower
    1.77
    lower
    1.73
     LOWER
    1.73
    LOWER
    1.52
     lowers
    1.18
     lowering
    1.05
     lowered
    1.04
     upper
    1.02
    Act Density 0.020%

    No Known Activations