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

    Neuronpedia

    INDEX
    Explanations

    strange, unusual phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    回忆
    0.41
    摊
    0.41
     RICO
    0.41
    韩国
    0.40
     Bradley
    0.40
    鬪
    0.39
    褴
    0.39
     Erick
    0.39
     Statutory
    0.38
     திரை
    0.38
    POSITIVE LOGITS
     swans
    0.70
     Strange
    0.56
     Phi
    0.52
     swan
    0.51
    Strange
    0.50
    Phi
    0.49
     Swans
    0.49
     strange
    0.49
     insane
    0.47
     bee
    0.46
    Act Density 0.000%

    No Known Activations