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

    Neuronpedia

    INDEX
    Explanations

    itinerary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stim
    -0.06
    숙
    -0.06
     části
    -0.06
     convex
    -0.06
     мар
    -0.06
     troubled
    -0.06
     بول
    -0.06
     pane
    -0.06
    Sample
    -0.06
    食
    -0.06
    POSITIVE LOGITS
    илась
    0.07
     MessageType
    0.07
     euros
    0.06
    вищ
    0.06
    -task
    0.06
    	V
    0.06
    .Sprintf
    0.06
    ="${
    0.06
     involving
    0.06
    超过
    0.06
    Act Density 0.030%

    No Known Activations