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

    Neuronpedia

    INDEX
    Explanations

    rating/score/grade

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /types
    -0.07
    �
    -0.06
     formed
    -0.06
     Highway
    -0.06
     Suite
    -0.06
     Bow
    -0.06
    [table
    -0.06
     [["
    -0.06
     stories
    -0.06
    Recently
    -0.06
    POSITIVE LOGITS
     circumcision
    0.07
     trước
    0.06
    既
    0.06
     blacks
    0.06
     "','"
    0.06
     Peyton
    0.06
     tangent
    0.06
     İç
    0.06
    menuItem
    0.06
    .CompareTo
    0.06
    Act Density 0.057%

    No Known Activations