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

    Neuronpedia

    INDEX
    Explanations

    centered at the origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     privy
    0.40
     defining
    0.37
     Positions
    0.37
     Parliamentary
    0.36
    defining
    0.35
     প্রা
    0.35
     definitive
    0.35
     polluted
    0.34
     अधि
    0.34
     monetization
    0.34
    POSITIVE LOGITS
    Origin
    1.22
     Origin
    1.15
     origin
    1.14
    origin
    1.09
     ORIG
    1.01
    ORIG
    0.92
     origen
    0.90
    Origins
    0.87
     origem
    0.86
     origins
    0.83
    Act Density 0.004%

    No Known Activations