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

    Neuronpedia

    INDEX
    Explanations

    Formula 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Xbox
    0.69
     PlayStation
    0.62
     Ball
    0.62
     Timberwolves
    0.62
     Game
    0.61
     susah
    0.61
     Har
    0.59
     Activision
    0.59
    Sky
    0.59
     can
    0.58
    POSITIVE LOGITS
     Bildung
    0.61
    溶液
    0.60
     renormalization
    0.55
     জড়িত
    0.54
    决定
    0.53
    }{-
    0.52
     اقتص
    0.52
    лянчук
    0.52
     Entscheidung
    0.52
    cheidung
    0.52
    Act Density 0.004%

    No Known Activations