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

    Neuronpedia

    INDEX
    Explanations

    Exercise and fitness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     polarity
    -0.07
    .ol
    -0.07
     Loch
    -0.06
     Uber
    -0.06
     Thames
    -0.06
    dock
    -0.06
    fst
    -0.06
     Maver
    -0.06
    _aspect
    -0.06
    leys
    -0.06
    POSITIVE LOGITS
     Học
    0.06
     уд
    0.06
    로운
    0.06
     Yunan
    0.06
    料無料
    0.06
    _mut
    0.06
    본
    0.06
    Outlet
    0.06
    ınca
    0.06
    XI
    0.06
    Act Density 0.011%

    No Known Activations