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

    Neuronpedia

    INDEX
    Explanations

    Stadt and related German city terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     불구하고
    1.71
    та
    1.68
    问题
    1.59
    ১
    1.58
    ated
    1.50
     Astrology
    1.45
     Commandments
    1.45
    led
    1.40
     Timurtaş
    1.39
    ้
    1.39
    POSITIVE LOGITS
    ل
    2.02
    ায়
    1.64
    podob
    1.63
    kampf
    1.52
    なに
    1.51
    ু
    1.49
    dag
    1.48
    kamer
    1.48
    ান
    1.47
    υ
    1.46
    Act Density 0.007%

    No Known Activations