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

    Neuronpedia

    INDEX
    Explanations

    Unrealistic beauty standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    埙
    -0.07
     Pixar
    -0.07
     cname
    -0.07
    疏导
    -0.07
    ()));↵
    -0.07
     █
    -0.06
    *)((
    -0.06
    펄
    -0.06
    政府采购
    -0.06
     площад
    -0.06
    POSITIVE LOGITS
    stein
    0.08
    JECTED
    0.07
    nect
    0.07
    🚼
    0.07
    ilit
    0.07
    atics
    0.07
    three
    0.07
    .blue
    0.07
    .puts
    0.06
     succession
    0.06
    Act Density 0.063%

    No Known Activations