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

    Neuronpedia

    INDEX
    Explanations

    announcement and release

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deriva
    0.72
     tolerancia
    0.71
     homework
    0.71
     સલા
    0.70
    व्यव
    0.69
     खाने
    0.68
    लोत
    0.68
     choroby
    0.68
    ડો
    0.67
     TreeSet
    0.66
    POSITIVE LOGITS
     release
    2.51
     releasing
    2.28
     Release
    2.28
    release
    2.24
    Release
    2.23
     releases
    2.23
     released
    2.10
     RELEASE
    1.95
     Releases
    1.92
     announcement
    1.87
    Act Density 0.888%

    No Known Activations