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

    Neuronpedia

    INDEX
    Explanations

    base case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অপ্র
    0.75
     box
    0.66
     current
    0.65
     appreciation
    0.63
     equipment
    0.62
     Box
    0.61
     reach
    0.61
     resources
    0.60
     stage
    0.59
     spoils
    0.59
    POSITIVE LOGITS
    พี
    0.69
    Հ
    0.66
     суу
    0.63
    Iniciar
    0.63
    喤
    0.61
    ély
    0.61
    MsgCallBack
    0.61
    pase
    0.60
    ígenes
    0.60
     Hồng
    0.59
    Act Density 0.197%

    No Known Activations