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

    Neuronpedia

    INDEX
    Explanations

    lists, foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Geometry
    0.49
    వ్వు
    0.46
    веря
    0.45
     Flights
    0.43
     ഡോ
    0.43
     Laboratory
    0.42
     Cruise
    0.42
     Labour
    0.42
     Fantastic
    0.42
     Therapy
    0.41
    POSITIVE LOGITS
     दलित
    0.48
    របស់
    0.44
    ських
    0.44
    repet
    0.43
    ವರ
    0.42
     був
    0.41
    ರಿನ
    0.41
    Rein
    0.41
     کے
    0.40
     солдат
    0.40
    Act Density 0.017%

    No Known Activations