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

    Neuronpedia

    INDEX
    Explanations

    regulatory/suppression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     committees
    -0.07
     Variety
    -0.07
     Cafe
    -0.07
     Erd
    -0.07
    權益
    -0.07
     fry
    -0.07
     quyền
    -0.07
    	ss
    -0.07
    -produced
    -0.06
     irritation
    -0.06
    POSITIVE LOGITS
    .bel
    0.07
     urls
    0.06
     memiliki
    0.06
    弹簧
    0.06
    ssp
    0.06
     resil
    0.06
    Selection
    0.06
     areas
    0.06
    apolis
    0.06
    шел
    0.06
    Act Density 0.013%

    No Known Activations