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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.86
     P
    0.74
    /
    0.72
     typically
    0.71
    -
    0.70
     C
    0.68
     $
    0.66
     K
    0.66
     U
    0.65
     which
    0.65
    POSITIVE LOGITS
     porque
    1.07
     omdat
    1.04
    并且
    1.03
    aunque
    1.03
     çünkü
    1.02
     क्योंकि
    1.02
     cuando
    1.01
    porque
    1.01
    而且
    1.00
    並且
    0.99
    Act Density 0.161%

    No Known Activations