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

    Neuronpedia

    INDEX
    Explanations

    race and health disparities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Home
    -0.08
     attenuation
    -0.07
    -middle
    -0.07
     repo
    -0.07
     переда
    -0.07
    Resistance
    -0.07
     jika
    -0.07
     metrů
    -0.07
    ;background
    -0.06
    Fabric
    -0.06
    POSITIVE LOGITS
    \core
    0.07
    एम
    0.07
    .sulake
    0.06
    .DecimalField
    0.06
     absl
    0.06
    /nav
    0.06
    SWEP
    0.06
    ==$
    0.06
    _HERSHEY
    0.06
     Jazeera
    0.06
    Act Density 0.021%

    No Known Activations