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

    Neuronpedia

    INDEX
    Explanations

    city locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.40
     in
    0.40
     as
    0.36
    k
    0.35
    رك
    0.34
    it
    0.33
    ковский
    0.33
    ee
    0.33
     ت
    0.32
    茥
    0.32
    POSITIVE LOGITS
     you
    0.39
     mumbai
    0.35
     gaya
    0.35
     miasta
    0.34
     niya
    0.32
     superficially
    0.32
    <0x8C>
    0.32
     seductive
    0.32
     soltanto
    0.32
     jums
    0.32
    Act Density 0.096%

    No Known Activations