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

    Neuronpedia

    INDEX
    Explanations

    10

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    人員
    -0.06
     �
    -0.06
     Rein
    -0.06
    퓨
    -0.06
    ypad
    -0.06
    대의
    -0.06
     предлож
    -0.06
     의해
    -0.06
     Bip
    -0.06
     роботи
    -0.06
    POSITIVE LOGITS
    30
    0.08
     Themes
    0.07
     guardian
    0.07
    attribute
    0.07
    CLASS
    0.07
     Kazakhstan
    0.06
    　　　　　　 　
    0.06
    lass
    0.06
    boxing
    0.06
    153
    0.06
    Act Density 0.011%

    No Known Activations