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

    Neuronpedia

    INDEX
    Explanations

    number of pages requested

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    0.69
    已
    0.56
    心
    0.53
    主題
    0.51
    在
    0.50
    spd
    0.49
    include
    0.49
    SI
    0.45
    金
    0.45
    ter
    0.44
    POSITIVE LOGITS
     of
    0.48
    ویه
    0.47
     scrut
    0.47
    стройство
    0.44
    ‌های
    0.42
     ماشین
    0.41
     Hopefully
    0.41
     والدین
    0.41
    vić
    0.41
     पाहिजे
    0.40
    Act Density 0.001%

    No Known Activations