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

    Neuronpedia

    INDEX
    Explanations

    Call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Serie
    0.45
    Serie
    0.43
     প্রমুখ
    0.40
    </ul>
    0.39
     lyrics
    0.39
     serie
    0.37
     sexta
    0.37
     série
    0.36
     روایت
    0.36
    usele
    0.36
    POSITIVE LOGITS
     प्रोटे
    0.43
     performing
    0.41
     mandatory
    0.38
     Performing
    0.38
     anesthesia
    0.38
    ректор
    0.37
     Просто
    0.37
     пут
    0.36
    Ef
    0.36
     ミ
    0.36
    Act Density 0.012%

    No Known Activations