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

    Neuronpedia

    INDEX
    Explanations

    New York City

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ron
    -0.07
     Liz
    -0.06
    enty
    -0.06
     ==
    -0.06
    řich
    -0.06
    ẳng
    -0.06
    RW
    -0.06
    olds
    -0.06
    Mor
    -0.06
     Fleming
    -0.06
    POSITIVE LOGITS
     pct
    0.07
     yasak
    0.06
    اده
    0.06
     مقدم
    0.06
     Township
    0.06
    pector
    0.06
    _behavior
    0.06
     церк
    0.06
     ACS
    0.06
    avior
    0.06
    Act Density 0.008%

    No Known Activations