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

    Neuronpedia

    INDEX
    Explanations

    United Kingdom and currencies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Language
    -0.07
     Tuy
    -0.07
     coy
    -0.07
    anyahu
    -0.07
    ­tion
    -0.06
    ich
    -0.06
     kunne
    -0.06
    èn
    -0.06
     Donation
    -0.06
    enu
    -0.06
    POSITIVE LOGITS
    //===
    0.08
    .toHexString
    0.06
    +)/
    0.06
     Surrey
    0.06
     [--
    0.06
    :"-
    0.06
     bardzo
    0.06
     SCORE
    0.06
     عاما
    0.06
    ########################################
    0.06
    Act Density 0.935%

    No Known Activations