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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    வ்வேறு
    0.79
     sue
    0.79
     वर्त
    0.79
     belie
    0.75
     Nhưng
    0.75
     القيام
    0.74
     Loyal
    0.74
     walled
    0.72
    घरों
    0.72
    গঞ্জে
    0.72
    POSITIVE LOGITS
    亡
    0.93
    गारी
    0.87
    weekday
    0.84
     Palash
    0.82
    "_
    0.81
     памяти
    0.79
    Ari
    0.79
     የስ
    0.79
    Շ
    0.79
    উত্তরঃ
    0.78
    Act Density 0.239%

    No Known Activations