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

    Neuronpedia

    INDEX
    Explanations

    Play movies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ν
    0.56
    ET
    0.55
    多い
    0.54
    д
    0.54
    radians
    0.51
    nid
    0.51
    Decimal
    0.50
    out
    0.50
    iteration
    0.50
    ER
    0.49
    POSITIVE LOGITS
    сь
    0.52
    ң
    0.51
    сім
    0.51
    ंशिक
    0.51
     fandom
    0.49
     Пере
    0.49
     demise
    0.48
    ‌است
    0.48
    ość
    0.47
     Верх
    0.47
    Act Density 0.004%

    No Known Activations