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

    Neuronpedia

    INDEX
    Explanations

    numbers and days from to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +
    0.71
    &
    0.70
    或其他
    0.66
    -,
    0.62
    +-
    0.61
    +/
    0.60
    prone
    0.60
    \}-
    0.59
    maxcdn
    0.57
     चेहरे
    0.56
    POSITIVE LOGITS
     लेके
    0.81
     inclusive
    0.80
     thorough
    0.79
     inclus
    0.77
    axanthin
    0.75
    áus
    0.72
     έως
    0.72
     upto
    0.71
     शीतल
    0.69
     Inclusive
    0.69
    Act Density 0.111%

    No Known Activations