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

    Neuronpedia

    INDEX
    Explanations

    references to boilers and furnaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    boiler reactor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stick
    -0.56
    Circ
    -0.52
     Nog
    -0.50
    sticks
    -0.50
     sticky
    -0.50
    Demografie
    -0.49
     kasarigan
    -0.48
     Heath
    -0.48
     Circ
    -0.48
    pleft
    -0.48
    POSITIVE LOGITS
     reactor
    0.68
     furnace
    0.67
     sessionFactory
    0.63
     boiler
    0.59
     furnaces
    0.59
     REACTOR
    0.59
     Reactor
    0.58
     Boiler
    0.58
     engine
    0.56
     Engine
    0.56
    Act Density 0.008%

    No Known Activations