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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encoder
    -0.08
     Constr
    -0.07
     conv
    -0.07
     coffee
    -0.07
    	dialog
    -0.07
    相机
    -0.07
    -node
    -0.07
     DOC
    -0.07
    ✖
    -0.07
    Mongo
    -0.07
    POSITIVE LOGITS
    툼
    0.07
     lists
    0.07
    ughs
    0.07
    甚至连
    0.07
    icrous
    0.07
     exemptions
    0.07
    랖
    0.06
     sẵ
    0.06
    绋
    0.06
    athering
    0.06
    Act Density 0.002%

    No Known Activations