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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grandma
    -0.07
    .zz
    -0.06
     wishlist
    -0.06
    TestFixture
    -0.06
     řek
    -0.06
     가족
    -0.06
    ินเด
    -0.06
    rne
    -0.06
    Uvs
    -0.06
     verwendet
    -0.06
    POSITIVE LOGITS
    uely
    0.08
    اخ
    0.07
    ADA
    0.07
    acılık
    0.06
    art
    0.06
     recycle
    0.06
    _csv
    0.06
     дорож
    0.06
    285
    0.06
    .argv
    0.06
    Act Density 0.004%

    No Known Activations