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

    Neuronpedia

    INDEX
    Explanations

    day 1 itineraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    0.57
    uí
    0.55
    ত
    0.51
    ták
    0.50
    heny
    0.48
    рд
    0.47
    Петер
    0.47
     али
    0.47
     ५
    0.47
    ubine
    0.47
    POSITIVE LOGITS
    0.71
     Fintech
    0.67
     Marketing
    0.51
     C
    0.49
     Choosing
    0.49
     What
    0.48
     Bridal
    0.47
     Nutrition
    0.46
     How
    0.46
     przesz
    0.46
    Act Density 0.006%

    No Known Activations