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

    Neuronpedia

    INDEX
    Explanations

    ensure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mix
    -0.07
    	↵
    -0.06
    		↵
    -0.06
     TOUCH
    -0.06
     Bru
    -0.06
    /ic
    -0.06
     sno
    -0.06
    ulant
    -0.06
     fres
    -0.06
    spotify
    -0.06
    POSITIVE LOGITS
    .....
    0.08
     ratified
    0.07
    bakan
    0.07
     Monthly
    0.06
    ительно
    0.06
    kuk
    0.06
    ....
    0.06
    Prefix
    0.06
    NavigationBar
    0.06
    .Image
    0.06
    Act Density 0.430%

    No Known Activations