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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тиров
    -0.07
     sided
    -0.07
     ire
    -0.06
     kidney
    -0.06
    інг
    -0.06
    Fair
    -0.06
    Vin
    -0.06
    ад
    -0.06
    Db
    -0.06
    svm
    -0.06
    POSITIVE LOGITS
     hỗn
    0.07
    ็กชาย
    0.07
    _GRAY
    0.06
    Measure
    0.06
     examinations
    0.06
    FULL
    0.06
     Kullan
    0.06
     OTHER
    0.06
     zač
    0.06
     XCTAssertTrue
    0.06
    Act Density 0.001%

    No Known Activations