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

    Neuronpedia

    INDEX
    Explanations

    third

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overlays
    -0.07
     درمان
    -0.07
     park
    -0.06
    anchor
    -0.06
    _buckets
    -0.06
     przy
    -0.06
    伝
    -0.06
    pesan
    -0.06
     England
    -0.06
     Dealer
    -0.06
    POSITIVE LOGITS
     дво
    0.07
    (states
    0.07
     justified
    0.06
    _TRANSACTION
    0.06
    .course
    0.06
    	Route
    0.06
    NavLink
    0.06
     classmates
    0.06
     ensures
    0.06
     militar
    0.06
    Act Density 0.005%

    No Known Activations