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

    Neuronpedia

    INDEX
    Explanations

    prevents wasted effort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     отвеча
    0.39
    dehyde
    0.38
    claimer
    0.38
     rápido
    0.38
    তিন
    0.37
    真的
    0.37
     altogether
    0.37
     начала
    0.36
     संहिता
    0.36
     Latex
    0.36
    POSITIVE LOGITS
     sque
    0.49
     quelqu
    0.45
    Importance
    0.44
    AAPL
    0.41
    importance
    0.40
    وق
    0.39
     Appalachian
    0.39
    рор
    0.39
     thoughtfulness
    0.37
     сле
    0.37
    Act Density 0.002%

    No Known Activations