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

    Neuronpedia

    INDEX
    Explanations

    material properties or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ści
    0.52
     ನಿಮಗೆ
    0.49
     স্পষ্ট
    0.47
     మీకు
    0.45
     ನಿಮ್ಮ
    0.45
    ógł
    0.45
     którą
    0.45
     পাতার
    0.44
    š
    0.43
    ção
    0.42
    POSITIVE LOGITS
     shod
    0.44
     marriages
    0.44
    wives
    0.42
    ﻫ
    0.42
     alles
    0.41
     ebenso
    0.41
     conse
    0.41
     steels
    0.40
     esposa
    0.40
     mergers
    0.40
    Act Density 0.007%

    No Known Activations