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

    Neuronpedia

    INDEX
    Explanations

    measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.98
     réguli
    -0.97
     poichè
    -0.95
    berdayakan
    -0.91
    rungsseite
    -0.91
     feroit
    -0.91
     automatiques
    -0.91
     leçon
    -0.91
     étoit
    -0.90
     rempliss
    -0.90
    POSITIVE LOGITS
     “
    0.86
     "
    0.78
     ‘
    0.66
     final
    0.59
     local
    0.59
     National
    0.58
     United
    0.57
     '
    0.57
     human
    0.57
     American
    0.56
    Act Density 0.335%

    No Known Activations