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

    Neuronpedia

    INDEX
    Explanations

    cities in India and Pakistan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hitth
    0.37
    Ziel
    0.37
     jednom
    0.35
    NIH
    0.35
     Stoppers
    0.35
     हौ
    0.35
     छेद
    0.35
     disebut
    0.34
    zik
    0.34
    ikt
    0.33
    POSITIVE LOGITS
     pwd
    0.37
    优惠
    0.36
     ores
    0.35
     goodies
    0.35
     preferential
    0.35
     xmas
    0.35
    ורה
    0.33
    Allocation
    0.33
     magnetite
    0.33
     upto
    0.33
    Act Density 0.000%

    No Known Activations