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

    Neuronpedia

    INDEX
    Explanations

    you want to know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intéressant
    1.04
    aquest
    0.98
    르는
    0.93
     Selanjutnya
    0.92
     célèbre
    0.90
     преступ
    0.89
    </b>
    0.89
    tweets
    0.89
     proposent
    0.89
    čně
    0.88
    POSITIVE LOGITS
    erweise
    1.02
     outweigh
    0.96
     accrued
    0.96
    га
    0.91
    👏
    0.89
    гаа
    0.88
    বান্ধ
    0.87
     humidifier
    0.86
    ных
    0.86
     reassuring
    0.85
    Act Density 0.276%

    No Known Activations