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

    Neuronpedia

    INDEX
    Explanations

    p

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    当地
    -0.08
    带领
    -0.07
     qreal
    -0.07
     Bek
    -0.07
     undef
    -0.06
    	ArrayList
    -0.06
     生
    -0.06
    精确
    -0.06
    @interface
    -0.06
     Leopard
    -0.06
    POSITIVE LOGITS
    �
    0.07
    僔
    0.07
    ッシ
    0.07
    formats
    0.07
     pist
    0.07
    退役
    0.07
     Johan
    0.07
     변
    0.07
    竞
    0.07
     السلام
    0.07
    Act Density 0.057%

    No Known Activations