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

    Neuronpedia

    INDEX
    Explanations

    currency totals and sums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CrossRef
    0.39
    सनीय
    0.34
    🍈
    0.34
    🫤
    0.34
     jí
    0.33
    渑
    0.33
     attenuated
    0.32
    📔
    0.32
    🛹
    0.31
    jén
    0.31
    POSITIVE LOGITS
     total
    0.59
     sum
    0.57
    合計
    0.52
    total
    0.51
    sum
    0.49
     SUM
    0.48
     Total
    0.46
     suma
    0.45
     Sum
    0.44
     toplam
    0.44
    Act Density 0.016%

    No Known Activations