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

    Neuronpedia

    INDEX
    Explanations

    world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zahl
    -0.07
     vertex
    -0.07
     ση
    -0.07
     spectrum
    -0.06
     consecutive
    -0.06
     Spectrum
    -0.06
     broadcasts
    -0.06
     electroly
    -0.06
     headline
    -0.06
     кораб
    -0.06
    POSITIVE LOGITS
     unified
    0.07
    	level
    0.07
    (World
    0.06
    woman
    0.06
     dodge
    0.06
     geld
    0.06
     Denied
    0.06
     fict
    0.06
     ΠΡ
    0.06
    osoph
    0.06
    Act Density 0.011%

    No Known Activations