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

    Neuronpedia

    INDEX
    Explanations

    metropolitan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NGO
    -0.07
     leaking
    -0.07
    ایند
    -0.07
     Shoulder
    -0.07
    �
    -0.06
    或者
    -0.06
     Cancel
    -0.06
     background
    -0.06
     enfer
    -0.06
    ance
    -0.06
    POSITIVE LOGITS
     Metropolitan
    0.10
     metropolitan
    0.09
     metro
    0.09
    .Metro
    0.08
     Metro
    0.08
    Metro
    0.08
    ropolitan
    0.07
    teri
    0.07
    packing
    0.07
     rozh
    0.07
    Act Density 0.007%

    No Known Activations