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

    Neuronpedia

    INDEX
    Explanations

    Persian text processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kę
    1.00
     również
    0.97
     uključ
    0.97
     også
    0.94
     mlijeka
    0.94
     koriste
    0.93
     gór
    0.89
     događ
    0.89
     wyświet
    0.88
     wody
    0.87
    POSITIVE LOGITS
     به
    1.13
     در
    1.05
     و
    1.02
     پ
    0.91
     از
    0.91
     چه
    0.89
     ب
    0.86
     آن
    0.85
     بر
    0.84
     م
    0.83
    Act Density 0.016%

    No Known Activations