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

    Neuronpedia

    INDEX
    Explanations

    but however

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pois
    0.49
     supported
    0.47
     infine
    0.43
    ുകൊണ്ട്
    0.43
     причем
    0.43
     takže
    0.42
     گئی۔
    0.42
     والتي
    0.42
     있고
    0.40
     pedibusque
    0.39
    POSITIVE LOGITS
     nhưng
    2.94
     ولكن
    2.83
     but
    2.81
     แต่
    2.80
     लेकिन
    2.78
     lakini
    2.67
     mutta
    2.61
     ngunit
    2.58
     لكن
    2.56
     But
    2.53
    Act Density 0.053%

    No Known Activations