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

    Neuronpedia

    INDEX
    Explanations

    Persian words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mga
    1.14
     unele
    1.13
     capacità
    1.04
    ຄວາມ
    1.04
     toate
    1.03
     Mga
    0.98
     모든
    0.96
     types
    0.95
     aspetto
    0.95
    Mga
    0.95
    POSITIVE LOGITS
     را
    1.20
     مانند
    1.17
     برای
    1.13
     بوده
    1.09
     باشد
    1.09
     در
    1.08
     قابل
    1.08
     و
    1.05
     دارد
    1.03
     tersebut
    1.03
    Act Density 0.004%

    No Known Activations