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

    Neuronpedia

    INDEX
    Explanations

    test cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Atelier
    0.41
    TestSuite
    0.40
     Cybersecurity
    0.40
     Cuisine
    0.39
    0.39
    替え
    0.38
     Auxiliary
    0.38
     André
    0.37
    cloak
    0.37
     Clubhouse
    0.37
    POSITIVE LOGITS
     الذي
    0.42
    $.)
    0.41
     algebraica
    0.41
     бъ
    0.40
     أن
    0.40
     ajust
    0.39
     aset
    0.39
     möglichen
    0.39
    %","
    0.38
    .].
    0.38
    Act Density 0.002%

    No Known Activations