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

    Neuronpedia

    INDEX
    Explanations

    first option in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    šie
    0.39
    $
    0.38
     territory
    0.38
     какое
    0.38
     Далее
    0.37
     {/*
    0.36
     ছুর
    0.36
     функция
    0.36
    केंद्रीय
    0.36
    city
    0.35
    POSITIVE LOGITS
     pilihan
    0.43
     mø
    0.43
     konkur
    0.42
    藥
    0.41
     제공
    0.41
    ۹
    0.40
     plantas
    0.40
     plantes
    0.40
     steward
    0.40
     các
    0.40
    Act Density 0.034%

    No Known Activations