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

    Neuronpedia

    INDEX
    Explanations

    process description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     милли
    -0.07
     accompany
    -0.06
     list
    -0.06
     permits
    -0.06
    sigma
    -0.06
    获得
    -0.06
     growth
    -0.06
     Sek
    -0.06
     Plasma
    -0.06
    -down
    -0.06
    POSITIVE LOGITS
    invalidate
    0.07
    政
    0.07
     nhìn
    0.07
    okers
    0.06
     blackjack
    0.06
     تد
    0.06
    nr
    0.06
    ноп
    0.06
    TARGET
    0.06
     впол
    0.06
    Act Density 0.088%

    No Known Activations