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

    Neuronpedia

    INDEX
    Explanations

    hopefully this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    giant
    0.50
     вони
    0.46
     enfermo
    0.45
    meet
    0.44
     він
    0.42
     وہ
    0.42
     یق
    0.42
    studies
    0.41
     apie
    0.40
    Voids
    0.40
    POSITIVE LOGITS
     вашего
    0.46
     gardening
    0.43
    是你
    0.42
    これから
    0.42
    이스
    0.42
     matou
    0.42
     உங்க
    0.41
    等你
    0.41
    你的
    0.41
    的用户
    0.40
    Act Density 0.004%

    No Known Activations