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

    Neuronpedia

    INDEX
    Explanations

    amp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    овор
    -0.07
     Fo
    -0.07
     крови
    -0.07
     Adrian
    -0.07
    种类
    -0.07
     toReturn
    -0.07
    相关规定
    -0.06
    (vis
    -0.06
     cott
    -0.06
    ผล
    -0.06
    POSITIVE LOGITS
    לית
    0.07
    _detected
    0.07
    嵯
    0.07
     triang
    0.07
    �
    0.07
    _weights
    0.07
     ons
    0.07
     recognizable
    0.07
     herramient
    0.07
    _printer
    0.07
    Act Density 0.011%

    No Known Activations