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

    Neuronpedia

    INDEX
    Explanations

    technical abbreviations and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Reservation
    0.43
     जलाशय
    0.42
    錬
    0.41
    সজ্জিত
    0.41
     ہاں
    0.41
     कंग
    0.40
    donate
    0.40
     estatales
    0.40
    Спасибо
    0.39
     Есть
    0.39
    POSITIVE LOGITS
     OS
    0.44
    PX
    0.44
     comput
    0.44
     DEX
    0.43
     SDK
    0.42
    BGR
    0.41
    기를
    0.40
     ín
    0.40
     PX
    0.39
     DES
    0.39
    Act Density 0.406%

    No Known Activations