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

    Neuronpedia

    INDEX
    Explanations

    generative adversarial networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whitelist
    -0.07
     Ged
    -0.07
     firmalar
    -0.07
     insanların
    -0.06
    miyor
    -0.06
     Kürt
    -0.06
     майбут
    -0.06
    üyük
    -0.06
    (parts
    -0.06
     принцип
    -0.06
    POSITIVE LOGITS
    itled
    0.07
    ottenham
    0.07
     advis
    0.07
     Interr
    0.07
    _Point
    0.07
    VERSE
    0.07
    فی
    0.07
    ernals
    0.07
     Def
    0.07
     Surre
    0.07
    Act Density 0.001%

    No Known Activations