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

    Neuronpedia

    INDEX
    Explanations

    initial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elect
    -0.07
    onta
    -0.07
    ominated
    -0.07
     Ανα
    -0.07
    desired
    -0.06
     gere
    -0.06
     Plzeň
    -0.06
     hoax
    -0.06
     gint
    -0.06
    likes
    -0.06
    POSITIVE LOGITS
     Dự
    0.08
     sàn
    0.06
    cac
    0.06
     централь
    0.06
    (menu
    0.06
     Pry
    0.06
     subscriber
    0.06
     formation
    0.06
    ุน
    0.06
     boto
    0.06
    Act Density 0.018%

    No Known Activations