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

    Neuronpedia

    INDEX
    Explanations

    write

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
     Georgia
    -0.08
     Metro
    -0.08
     Renewable
    -0.07
     geothermal
    -0.07
     Pauline
    -0.07
     kidn
    -0.07
     restaurant
    -0.07
     Conversations
    -0.07
     renewable
    -0.07
    POSITIVE LOGITS
    overwrite
    0.09
     PUT
    0.09
     ущер
    0.09
    kus
    0.09
     سای
    0.09
    Overwrite
    0.08
    eyan
    0.08
    дэр
    0.08
     تاثیر
    0.08
     آئے
    0.08
    Act Density 0.002%
    No Known Activations