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

    Neuronpedia

    INDEX
    Explanations

    lists named prefixes or authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fallout
    1.06
     Capricorn
    1.02
     in
    1.00
     PowerPoint
    0.97
     SWOT
    0.97
     to
    0.96
     Siberian
    0.94
     or
    0.92
     Avengers
    0.91
     Recherche
    0.91
    POSITIVE LOGITS
    <unused985>
    0.92
     beerCount
    0.87
    通常の
    0.84
    <unused682>
    0.84
     احد
    0.83
     кілька
    0.80
    同樣
    0.80
     використання
    0.80
    <unused355>
    0.79
    シンプル
    0.78
    Act Density 0.000%

    No Known Activations