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

    Neuronpedia

    INDEX
    Explanations

    at least a number or frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    al
    2.32
    astype
    2.25
     StyleSheet
    2.21
     glory
    2.15
    다
    2.13
    urpose
    2.10
     दरअसल
    2.10
    據
    2.08
    zelf
    2.07
    adhar
    2.04
    POSITIVE LOGITS
    পক্ষে
    3.16
    ف
    2.57
     Temos
    2.26
     vorhand
    2.09
    अप
    2.03
     који
    1.99
     workbench
    1.95
    スマス
    1.95
    സ്സ
    1.95
    तमंद
    1.95
    Act Density 0.087%

    No Known Activations