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

    Neuronpedia

    INDEX
    Explanations

    interdependencies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kwam
    -0.10
     wk
    -0.08
     Александр
    -0.08
    asarkan
    -0.08
     restarting
    -0.08
    otland
    -0.08
     mün
    -0.08
     Largest
    -0.08
    ിരുന്നു
    -0.08
    吴
    -0.07
    POSITIVE LOGITS
     complement
    0.09
     complements
    0.09
     complemented
    0.08
     доп
    0.08
     enabling
    0.08
     tangible
    0.08
     compliment
    0.07
     discussed
    0.07
     ਨਾਲ
    0.07
     techniques
    0.07
    Act Density 0.107%

    No Known Activations