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

    Neuronpedia

    INDEX
    Explanations

    .GetType .getClass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nú
    -0.07
     cylinders
    -0.07
     куд
    -0.07
    .jsdelivr
    -0.07
    இ
    -0.07
    末端
    -0.07
     tasted
    -0.07
    uglify
    -0.07
    .metrics
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    bike
    0.08
    Square
    0.07
    arest
    0.07
     Germany
    0.07
    ,,,,
    0.07
    }))
    0.07
    Bug
    0.07
    雨
    0.07
     gorge
    0.06
    只是为了
    0.06
    Act Density 0.002%

    No Known Activations