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

    Neuronpedia

    INDEX
    Explanations

    doesn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بود
    0.50
    可能性がある
    0.47
    なのか
    0.44
     있지만
    0.44
     BUT
    0.43
     unattainable
    0.43
    もあり
    0.42
    했다
    0.42
     EXCEPT
    0.42
    我也是
    0.41
    POSITIVE LOGITS
     doesn
    2.77
     didn
    2.36
    doesn
    2.00
     Doesn
    1.91
    Doesn
    1.85
     doesnt
    1.73
     не
    1.72
     ikke
    1.71
     nicht
    1.68
     don
    1.66
    Act Density 0.706%

    No Known Activations