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

    Neuronpedia

    INDEX
    Explanations

    introductory texts or summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stam
    -0.09
    вол
    -0.08
     ист
    -0.08
     zwar
    -0.08
    sizeof
    -0.08
    thest
    -0.07
    جنب
    -0.07
     કારણે
    -0.07
    قان
    -0.07
     ورس
    -0.07
    POSITIVE LOGITS
     whatsoever
    0.12
     кроме
    0.10
     surprises
    0.09
    เลย
    0.09
     lagi
    0.08
    ble
    0.08
     nào
    0.08
     discern
    0.08
     except
    0.07
     sprake
    0.07
    Act Density 0.132%

    No Known Activations