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

    Neuronpedia

    INDEX
    Explanations

    explaining with as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thereby
    0.74
     Thereby
    0.54
    从而
    0.53
     zodat
    0.53
     რომლებიც
    0.51
    which
    0.49
     което
    0.46
     whiche
    0.46
    thus
    0.46
     WHICH
    0.46
    POSITIVE LOGITS
     क्योंकि
    0.73
     কেননা
    0.72
     especially
    0.71
     pues
    0.68
     ஏனெனில்
    0.67
    因为它
    0.66
     bởi
    0.66
    Especially
    0.66
     çünkü
    0.64
     Especially
    0.64
    Act Density 0.007%

    No Known Activations