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

    Neuronpedia

    INDEX
    Explanations

    shocking British monarch justifying projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    폭
    0.50
     lunchtime
    0.48
     bulky
    0.48
    시킨
    0.47
    फी
    0.47
    inę
    0.46
    ‌شده
    0.46
    纮
    0.46
    ترین
    0.46
    های
    0.45
    POSITIVE LOGITS
     vassals
    0.53
    raud
    0.51
    rá
    0.49
    ä
    0.47
    ry
    0.46
     bowels
    0.46
    ierls
    0.44
     dwellers
    0.44
    ars
    0.43
    මට
    0.43
    Act Density 0.000%

    No Known Activations