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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pinch
    -0.07
    _Back
    -0.07
     long
    -0.06
    我国
    -0.06
    兆
    -0.06
     deserving
    -0.06
    什么呢
    -0.06
     çek
    -0.06
    锡
    -0.06
    一站
    -0.06
    POSITIVE LOGITS
    (parameter
    0.07
    (common
    0.07
     ולא
    0.07
    לר
    0.07
     '"+
    0.07
    랄
    0.07
     حوالي
    0.07
    alary
    0.07
    �
    0.07
     설치
    0.07
    Act Density 0.043%

    No Known Activations