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

    Neuronpedia

    INDEX
    Explanations

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilty
    -0.07
     集
    -0.07
     ры
    -0.07
    	holder
    -0.06
     WIN
    -0.06
     حر
    -0.06
    アルバ
    -0.06
    教师
    -0.06
     ＼
    -0.06
     riding
    -0.06
    POSITIVE LOGITS
     CREATED
    0.07
     INCIDENTAL
    0.07
    _SORT
    0.07
     sights
    0.06
    acciones
    0.06
    สมเด
    0.06
    mongodb
    0.06
     unaffected
    0.06
    Classifier
    0.06
    _RENDERER
    0.06
    Act Density 0.001%

    No Known Activations