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

    Neuronpedia

    INDEX
    Explanations

    VAT and other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     גם
    0.45
    ても
    0.44
    ก็ได้
    0.41
     (~
    0.38
     अस्थ
    0.37
     అతని
    0.37
    Florida
    0.37
    에서도
    0.37
    หยุด
    0.37
     gefallen
    0.37
    POSITIVE LOGITS
    ўнай
    0.42
     Vat
    0.40
    VAT
    0.39
     თან
    0.39
    OCATION
    0.39
    countries
    0.38
     vat
    0.38
     Vaish
    0.38
     탐
    0.37
     отрасли
    0.36
    Act Density 0.000%

    No Known Activations