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

    Neuronpedia

    INDEX
    Explanations

    furnace

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paul
    -0.07
    角
    -0.07
     theoretically
    -0.07
     judicial
    -0.07
    ////////////
    -0.07
    Paul
    -0.06
     Tyler
    -0.06
     noop
    -0.06
     respective
    -0.06
     solo
    -0.06
    POSITIVE LOGITS
     furnished
    0.09
     furnish
    0.08
     Furn
    0.08
     furn
    0.07
    lum
    0.07
     furnace
    0.07
     參
    0.07
     useSelector
    0.07
    illusion
    0.07
     Muss
    0.06
    Act Density 0.002%

    No Known Activations