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

    Neuronpedia

    INDEX
    Explanations

    poverty, lower-income housing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -component
    -0.10
    components
    -0.09
     bire
    -0.09
     anis
    -0.08
    组件
    -0.08
    polar
    -0.08
    bac
    -0.08
    operators
    -0.08
    Quaternion
    -0.08
     radians
    -0.08
    POSITIVE LOGITS
     poverty
    0.15
     impover
    0.15
     गरीब
    0.14
     pobreza
    0.14
    贫
    0.14
     गरी
    0.14
    Affordable
    0.14
     Poverty
    0.13
     unemployed
    0.13
     despair
    0.13
    Act Density 0.062%

    No Known Activations