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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spaceship
    -0.07
     внут
    -0.07
     UIImage
    -0.07
     unicorn
    -0.07
     protest
    -0.06
     XCTAssertEqual
    -0.06
     ADDR
    -0.06
     Surround
    -0.06
     nrows
    -0.06
    Ster
    -0.06
    POSITIVE LOGITS
     postav
    0.07
    analytics
    0.07
    имв
    0.06
    dictionary
    0.06
    productos
    0.06
    quipment
    0.06
    Cannot
    0.06
     지방
    0.06
     дополнитель
    0.05
    Mp
    0.05
    Act Density 0.000%

    No Known Activations