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

    Neuronpedia

    INDEX
    Explanations

    plasmonic / metamaterials / resonance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .$\
    0.60
     Giac
    0.56
    hin
    0.55
     treadmill
    0.52
    的其他
    0.52
     pai
    0.50
    ,
    0.50
    enangkan
    0.50
    햐
    0.49
    zott
    0.48
    POSITIVE LOGITS
     работа
    0.67
    <0x95>
    0.60
    ﻟ
    0.58
    ﻧ
    0.57
     ع
    0.57
     OVER
    0.56
     entice
    0.55
     n
    0.54
     опти
    0.54
    </strong>
    0.53
    Act Density 0.008%

    No Known Activations