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

    Neuronpedia

    INDEX
    Explanations

    book titles and editions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     πίνακα
    0.36
     Worksheet
    0.33
    等は
    0.33
     лист
    0.32
     moan
    0.32
     útil
    0.32
     vragen
    0.32
     códigos
    0.32
     Februari
    0.32
     Список
    0.32
    POSITIVE LOGITS
     Edited
    0.36
    Hier
    0.34
     latter
    0.34
     VOLUME
    0.33
     readonly
    0.33
    subtitle
    0.33
     Featuring
    0.33
    ილი
    0.33
     WOMEN
    0.33
    zków
    0.33
    Act Density 0.004%

    No Known Activations