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

    Neuronpedia

    INDEX
    Explanations

    lists categorized and explained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meliputi
    0.39
     Covers
    0.35
    еру
    0.34
    ྵ
    0.34
    வின
    0.34
    щу
    0.33
    responsible
    0.33
    covers
    0.33
    uling
    0.33
    カバー
    0.32
    POSITIVE LOGITS
     arranged
    1.08
     packaged
    1.04
     wrapped
    0.99
     formatted
    0.96
     presented
    0.95
     delivered
    0.91
     filtered
    0.91
     rendered
    0.89
     separated
    0.89
     framed
    0.89
    Act Density 0.359%

    No Known Activations