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

    Neuronpedia

    INDEX
    Explanations

    dreaming of sustainable futures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quadrants
    0.99
     quadrant
    0.97
     Brookhaven
    0.97
     birthplace
    0.96
     erections
    0.96
     phosphatase
    0.95
     discrepancies
    0.94
    ্ড
    0.93
     childlike
    0.93
     tomography
    0.92
    POSITIVE LOGITS
     był
    1.07
    arı
    0.95
    čiu
    0.93
    ad
    0.89
     bună
    0.88
    ına
    0.88
    šana
    0.88
     dů
    0.87
    ang
    0.86
     ви
    0.86
    Act Density 0.002%

    No Known Activations