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

    Neuronpedia

    INDEX
    Explanations

    verb endings and conjugations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मिळाली
    0.56
     kullanıl
    0.55
    літи
    0.54
     تھیں
    0.54
    प्रिल
    0.52
     सांगितले
    0.51
     должно
    0.51
     ہوگی
    0.50
     जाईल
    0.50
     быть
    0.50
    POSITIVE LOGITS
    ando
    1.35
    ado
    1.16
    ada
    0.98
    ación
    0.97
    adora
    0.90
    ANDO
    0.89
    adores
    0.89
    ándose
    0.88
    adoras
    0.86
    ar
    0.86
    Act Density 0.069%

    No Known Activations