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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ExpectedConditions
    -0.06
    .DO
    -0.06
     망
    -0.06
    oví
    -0.06
     эксплуата
    -0.06
     zeigen
    -0.06
     आव
    -0.06
     möchte
    -0.06
     RU
    -0.06
    (edges
    -0.06
    POSITIVE LOGITS
    idi
    0.06
    去了
    0.06
    (chart
    0.06
    likle
    0.06
    530
    0.06
    ‡
    0.06
    _categories
    0.06
    สำค
    0.06
     nắng
    0.06
    Replacing
    0.06
    Act Density 0.000%

    No Known Activations