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

    Neuronpedia

    INDEX
    Explanations

    code and equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    letes
    -0.07
     palate
    -0.07
    =Y
    -0.07
    _Report
    -0.06
     trackers
    -0.06
     oyn
    -0.06
    (substr
    -0.06
     sư
    -0.06
    ]*)
    -0.06
     tapes
    -0.06
    POSITIVE LOGITS
    <!--<
    0.07
     testCase
    0.07
    	glm
    0.07
    	fd
    0.06
    skému
    0.06
    todo
    0.06
    住宅
    0.06
    間に
    0.06
     ​
    0.06
    Česk
    0.06
    Act Density 0.042%

    No Known Activations