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

    Neuronpedia

    INDEX
    Explanations

    Kas or Ks start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Instead
    0.38
     పై
    0.35
     vermek
    0.35
     Grounds
    0.34
     Instead
    0.33
     Sinne
    0.33
     grounds
    0.33
     Wieder
    0.33
    ferenz
    0.33
     স্বদেশ
    0.33
    POSITIVE LOGITS
    ারক
    0.39
     succeed
    0.38
     estampado
    0.37
     ஸ்ட
    0.37
    veget
    0.36
    ଣ୍
    0.36
    スタ
    0.36
     كس
    0.36
     Соб
    0.36
    笠
    0.35
    Act Density 0.004%

    No Known Activations