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

    Neuronpedia

    INDEX
    Explanations

    nobility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blinked
    -0.07
    Focus
    -0.07
    ())
↵
↵
    -0.06
    ucene
    -0.06
    damn
    -0.06
    \Factory
    -0.06
     Також
    -0.06
     budget
    -0.06
     čer
    -0.06
     CAD
    -0.06
    POSITIVE LOGITS
     arist
    0.09
    ipment
    0.07
     nob
    0.07
     hton
    0.07
     Supern
    0.06
    setBackground
    0.06
     dial
    0.06
     Nob
    0.06
     강남
    0.06
     yoktu
    0.06
    Act Density 0.015%

    No Known Activations