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

    Neuronpedia

    INDEX
    Explanations

    first, other, gives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    陥
    0.41
     हाउ
    0.40
     பருவ
    0.40
    すべての
    0.39
    ulnerable
    0.39
     treatises
    0.39
    ਲ
    0.39
    alls
    0.39
    ALL
    0.39
    Important
    0.38
    POSITIVE LOGITS
     erster
    0.54
     첫
    0.51
     eerste
    0.50
     prvi
    0.49
     pertama
    0.49
     pierwszym
    0.48
     scene
    0.46
     ensimmä
    0.45
     Первый
    0.45
     первого
    0.44
    Act Density 0.001%

    No Known Activations