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

    Neuronpedia

    INDEX
    Explanations

    comparative advantage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ઉત્
    0.38
     ଯ
    0.37
    ⅾ
    0.37
     چڑھ
    0.36
    他
    0.36
    ԁ
    0.35
    shade
    0.34
     سپور
    0.34
     wereld
    0.34
     doanh
    0.34
    POSITIVE LOGITS
     Ich
    0.43
    Ich
    0.41
    uje
    0.40
     పరీక్ష
    0.39
    Position
    0.39
     Ions
    0.39
     was
    0.38
     Parlament
    0.37
    )
    0.36
     Nota
    0.36
    Act Density 0.001%

    No Known Activations