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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (guid
    -0.07
     programma
    -0.06
     penalty
    -0.06
     parses
    -0.06
    ,(
    -0.06
    Yo
    -0.06
    人間
    -0.06
    {
    -0.06
    rames
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     MÜ
    0.06
     मदद
    0.06
     میلی
    0.06
     Naomi
    0.06
     dejtingsaj
    0.06
     Население
    0.06
     Sayı
    0.06
     NVIC
    0.06
     cigaret
    0.06
     usern
    0.05
    Act Density 0.147%

    No Known Activations