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

    Neuronpedia

    INDEX
    Explanations

    demand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myšlen
    -0.07
    率
    -0.07
    uilder
    -0.07
     hooks
    -0.06
     OSError
    -0.06
    ises
    -0.06
     استر
    -0.06
    inness
    -0.06
    стер
    -0.06
     Burke
    -0.06
    POSITIVE LOGITS
     demanded
    0.13
     demands
    0.12
     demanding
    0.12
     demand
    0.09
     Grades
    0.07
     empowered
    0.07
     Demand
    0.07
     làm
    0.07
     ult
    0.07
     poplat
    0.07
    Act Density 0.011%

    No Known Activations