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

    Neuronpedia

    INDEX
    Explanations

    Steam power and turbines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    heur
    -0.08
    rud
    -0.08
     intuition
    -0.08
     rew
    -0.08
    trait
    -0.07
    datatype
    -0.07
     etik
    -0.07
     偷
    -0.07
     পক্ষ
    -0.07
     curated
    -0.07
    POSITIVE LOGITS
     Steam
    0.10
     turbine
    0.10
     steam
    0.10
    Steam
    0.10
     furnace
    0.09
     coolant
    0.09
    舰
    0.08
     Quit
    0.08
    船
    0.08
     turbines
    0.08
    Act Density 0.006%

    No Known Activations