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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Saudi
    -0.07
     guided
    -0.07
     Nadu
    -0.07
     investigación
    -0.07
     Airbnb
    -0.06
    ww
    -0.06
     Ji
    -0.06
    _CLOSE
    -0.06
    	App
    -0.06
    .Constant
    -0.06
    POSITIVE LOGITS
     расстоя
    0.06
     Previously
    0.06
    _phi
    0.06
    ules
    0.06
    promo
    0.06
     mileage
    0.06
     급
    0.06
    	
↵
    0.06
    [prop
    0.06
    scss
    0.06
    Act Density 0.173%

    No Known Activations