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

    Neuronpedia

    INDEX
    Explanations

    ellen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lag
    -0.07
     immac
    -0.07
    .pagination
    -0.06
     xn
    -0.06
    昨
    -0.06
    expectException
    -0.06
     ав
    -0.06
     objection
    -0.06
     asym
    -0.06
     tab
    -0.06
    POSITIVE LOGITS
    ))==
    0.07
    .Automation
    0.07
    stu
    0.06
    KW
    0.06
     Walnut
    0.06
    conditional
    0.06
    money
    0.06
    Oil
    0.06
     Свят
    0.06
    ちゃん
    0.06
    Act Density 0.019%

    No Known Activations