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

    Neuronpedia

    INDEX
    Explanations

    language improves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    盜
    0.51
    盗
    0.43
     bungalows
    0.42
    มูล
    0.42
    しますが
    0.41
    шла
    0.41
    prisoners
    0.40
     মার
    0.40
    廨
    0.40
    嫘
    0.40
    POSITIVE LOGITS
    imiya
    0.51
     mitochond
    0.49
     miesią
    0.48
     xenon
    0.48
     educator
    0.47
     Magyar
    0.47
     vitesse
    0.47
     magyar
    0.46
     pharmac
    0.46
     económ
    0.46
    Act Density 0.002%

    No Known Activations