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

    Neuronpedia

    INDEX
    Explanations

    readthedocs documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.45
    denomination
    0.44
     कोटा
    0.42
    宅配
    0.39
    AVG
    0.39
    এল
    0.38
     MAGNET
    0.37
    ppermint
    0.37
    fromi
    0.37
    FLD
    0.37
    POSITIVE LOGITS
     Sphinx
    1.38
     sphinx
    1.29
    Sph
    1.16
    sphinx
    1.09
    readthedocs
    0.94
    toctree
    0.93
     Sph
    0.89
     sphing
    0.88
     Doc
    0.83
     doc
    0.83
    Act Density 0.008%

    No Known Activations