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

    Neuronpedia

    INDEX
    Explanations

    Egypt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ४
    -0.08
    (bs
    -0.07
    -ring
    -0.06
     απ
    -0.06
     brides
    -0.06
     Filip
    -0.06
     Nicolas
    -0.06
     draped
    -0.06
    orgeous
    -0.06
     Luther
    -0.06
    POSITIVE LOGITS
     archaeological
    0.07
    ственная
    0.06
     Discrim
    0.06
     alike
    0.06
     appointments
    0.06
     stati
    0.06
     bookstore
    0.06
     جغراف
    0.06
     sorte
    0.06
    HA
    0.06
    Act Density 0.071%

    No Known Activations