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

    Neuronpedia

    INDEX
    Explanations

    explains or discusses topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     projectors
    0.47
     ancillary
    0.46
     presumably
    0.44
     year
    0.44
     constituted
    0.42
     deformable
    0.42
     multiuser
    0.41
     assumed
    0.41
    шими
    0.41
     particuliers
    0.41
    POSITIVE LOGITS
    Discuss
    0.71
     Discuss
    0.66
     hvordan
    0.65
     discussing
    0.64
     Cómo
    0.64
     explicando
    0.62
     কিভাবে
    0.61
     discutir
    0.60
     איך
    0.60
     обсу
    0.59
    Act Density 0.033%

    No Known Activations