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

    Neuronpedia

    INDEX
    Explanations

    qualified healthcare or legal professional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ль
    1.22
     gewisse
    1.08
    훑
    1.05
    кции
    1.04
    Pokud
    0.99
    если
    0.98
    লির
    0.98
    엡
    0.97
     Utilisez
    0.97
    нон
    0.96
    POSITIVE LOGITS
    ב
    1.13
    .
    1.01
    oras
    0.95
    cares
    0.95
    ؟
    0.93
    ла
    0.92
     приме
    0.92
    eee
    0.91
    。「
    0.91
    oru
    0.90
    Act Density 0.066%

    No Known Activations