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

    Neuronpedia

    INDEX
    Explanations

    answer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mob
    -0.08
     ഇട
    -0.08
     qualche
    -0.07
     Papa
    -0.07
     ::=
    -0.07
     hochwertigen
    -0.07
    某
    -0.07
     spar
    -0.07
    有哪些
    -0.07
     {};
    -0.07
    POSITIVE LOGITS
     계속
    0.09
    Yep
    0.08
    òg
    0.08
     accordingly
    0.08
    ardless
    0.08
     entsprechend
    0.07
     답
    0.07
     indeed
    0.07
     соответствии
    0.07
     :)↵↵
    0.07
    Act Density 0.094%

    No Known Activations