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

    Neuronpedia

    INDEX
    Explanations

    the word "per" related to percentages

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

    percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asupra
    -0.29
    ↵↵
    -0.28
     Económica
    -0.27
     bangun
    -0.27
     destek
    -0.26
    rzez
    -0.26
    Kommentare
    -0.26
     primaire
    -0.25
     üzerine
    -0.25
    <eos>
    -0.25
    POSITIVE LOGITS
     EconPapers
    0.81
    RTCF
    0.74
    KommentareTeilen
    0.71
    fillType
    0.71
    𓋼
    0.71
    앫
    0.70
     daysTop
    0.70
     vPvB
    0.70
    :✨
    0.70
    <unused41>
    0.70
    Act Density 0.017%

    No Known Activations