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

    Neuronpedia

    INDEX
    Explanations

    which, которая, która

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     himself
    1.98
     केली
    1.69
     который
    1.62
     який
    1.61
     ktorý
    1.58
     koji
    1.57
     který
    1.51
     his
    1.51
     झाली
    1.50
     който
    1.49
    POSITIVE LOGITS
     која
    2.14
     koja
    1.99
     która
    1.90
     ktorá
    1.87
     которая
    1.85
     която
    1.83
     такая
    1.78
     была
    1.76
     должна
    1.72
     která
    1.72
    Act Density 0.089%

    No Known Activations