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

    Neuronpedia

    INDEX
    Explanations

    ch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ules
    -0.07
     pedestrians
    -0.07
    ugin
    -0.07
     Brigham
    -0.06
    ío
    -0.06
     sanitary
    -0.06
    <<"
    -0.06
    ughty
    -0.06
     ratio
    -0.06
    avra
    -0.06
    POSITIVE LOGITS
     Businesses
    0.06
     많은
    0.06
    _Variable
    0.06
     honoring
    0.06
     bilg
    0.06
     troll
    0.06
    =======↵
    0.06
    樣
    0.06
    trecht
    0.06
     SCREEN
    0.06
    Act Density 0.004%

    No Known Activations