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

    Neuronpedia

    INDEX
    Explanations

    Increasing/decreasing trends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    хьтан
    -0.91
     increasing
    -0.83
     Increasing
    -0.81
    Increasing
    -0.80
    GEBURTSDATUM
    -0.78
     increased
    -0.77
    LookAnd
    -0.76
    ArgumentParser
    -0.76
     increase
    -0.76
    increased
    -0.76
    POSITIVE LOGITS
    ly
    0.40
     niyang
    0.38
    什么呢
    0.36
     wort
    0.35
    vue
    0.34
     siyang
    0.33
     interacted
    0.33
    прият
    0.33
    ynka
    0.33
     cade
    0.33
    Act Density 0.003%

    No Known Activations