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

    Neuronpedia

    INDEX
    Explanations

    Scientific measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bucket
    -0.07
     مفهوم
    -0.06
    alloween
    -0.06
    산
    -0.06
     repositories
    -0.06
    _mtx
    -0.06
     Bag
    -0.06
    	Action
    -0.06
    ImageUrl
    -0.06
    .ListView
    -0.06
    POSITIVE LOGITS
    BF
    0.07
    後に
    0.06
     oluş
    0.06
    MeasureSpec
    0.06
    sembles
    0.06
     derog
    0.06
     "'.$
    0.06
    롭
    0.06
    Regions
    0.06
     recess
    0.06
    Act Density 0.008%

    No Known Activations