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

    Neuronpedia

    INDEX
    Explanations

    urban

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ritte
    -0.07
    soft
    -0.06
     madde
    -0.06
     мов
    -0.06
    .ALL
    -0.06
    izens
    -0.06
    िब
    -0.06
     symmetry
    -0.06
    ении
    -0.06
    eslint
    -0.06
    POSITIVE LOGITS
     lingering
    0.07
    getHeight
    0.06
     clubhouse
    0.06
     klin
    0.06
     Dig
    0.06
     Compar
    0.06
     HR
    0.06
    addr
    0.06
     incarcerated
    0.06
     hdf
    0.06
    Act Density 0.004%

    No Known Activations