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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.49
     this
    0.47
    ;
    0.46
    :
    0.43
     wept
    0.41
     ў
    0.40
     dieses
    0.38
     your
    0.37
    ),
    0.37
     these
    0.37
    POSITIVE LOGITS
     But
    0.72
     And
    0.66
     Nhưng
    0.65
     Including
    0.64
    but
    0.64
     पण
    0.62
     लेकिन
    0.60
     Mainly
    0.59
    But
    0.59
     אבל
    0.56
    Act Density 0.001%

    No Known Activations