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

    Neuronpedia

    INDEX
    Explanations

    Math operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Polygon
    -0.08
     Dreams
    -0.06
     tty
    -0.06
     cushion
    -0.06
    Artist
    -0.06
     SceneManager
    -0.06
    Authority
    -0.06
     پرداخت
    -0.06
     Assembly
    -0.06
     arcade
    -0.06
    POSITIVE LOGITS
     surveyed
    0.07
    -footer
    0.06
     alanında
    0.06
     underestimated
    0.06
     referring
    0.06
    ibern
    0.06
     carcin
    0.06
    خل
    0.06
    ابات
    0.06
     hộ
    0.05
    Act Density 0.005%

    No Known Activations