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

    Neuronpedia

    INDEX
    Explanations

    -ized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NICE
    -0.08
     eventualmente
    -0.08
     Therm
    -0.08
     ramas
    -0.08
     pthread
    -0.08
     Tips
    -0.08
     Pian
    -0.08
     enzymes
    -0.08
     శాఖ
    -0.08
    dispatcher
    -0.08
    POSITIVE LOGITS
    商品
    0.10
     femen
    0.09
     fémin
    0.09
     unnecessarily
    0.09
     femin
    0.08
    扱
    0.08
     वस्त
    0.08
     ಮಹಿಳ
    0.08
     kobiet
    0.08
     aspect
    0.08
    Act Density 0.006%

    No Known Activations