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

    Neuronpedia

    INDEX
    Explanations

    physical locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endforeach
    -0.07
    便利店
    -0.07
    悬念
    -0.07
    <Object
    -0.07
     signin
    -0.07
     recyclerView
    -0.07
     Rever
    -0.07
     f
    -0.07
    🎲
    -0.07
     render
    -0.07
    POSITIVE LOGITS
    非常重要
    0.08
    了他的
    0.07
    꿋
    0.07
    更高
    0.07
    _department
    0.07
    專
    0.07
    	ERROR
    0.07
    #define
    0.06
    (enum
    0.06
    .Low
    0.06
    Act Density 0.047%

    No Known Activations