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

    Neuronpedia

    INDEX
    Explanations

    is: namely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    等
    0.59
     आदि
    0.58
    etc
    0.57
     ইত্যাদি
    0.55
     Phenomena
    0.53
    そして
    0.52
    など
    0.51
     etc
    0.51
     इत्यादि
    0.50
    等は
    0.49
    POSITIVE LOGITS
    :
    0.90
     twofold
    0.89
     namely
    0.84
     threefold
    0.79
     figuring
    0.76
     how
    0.74
     quello
    0.73
     those
    0.72
     obtaining
    0.71
    ：“
    0.69
    Act Density 0.445%

    No Known Activations