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

    Neuronpedia

    INDEX
    Explanations

    foreign scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsEnabled
    0.39
    בער
    0.38
    owskiego
    0.37
    tní
    0.37
     things
    0.36
     basics
    0.36
    是什么
    0.36
    RequestListener
    0.36
     $^{
    0.35
    stice
    0.35
    POSITIVE LOGITS
     ಕಾ
    0.37
     ভিন্ন
    0.36
     பெ
    0.35
     சக
    0.34
     lö
    0.34
     لوبوي
    0.34
    不僅
    0.34
    Vari
    0.33
    、「
    0.33
    тип
    0.33
    Act Density 0.446%

    No Known Activations