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

    Neuronpedia

    INDEX
    Explanations

    attention, sequential processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مام
    0.46
    urchase
    0.46
     callus
    0.45
     التج
    0.41
     Louise
    0.41
     мам
    0.40
    ৩৭
    0.40
     categoryService
    0.40
     संग्राम
    0.40
     পূজা
    0.40
    POSITIVE LOGITS
    Attention
    1.01
     attention
    1.00
     Attention
    1.00
    RNN
    0.92
     sequence
    0.89
     seq
    0.88
     RNN
    0.86
    attention
    0.84
     sequences
    0.81
    Sequence
    0.81
    Act Density 0.087%

    No Known Activations