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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JUL
    -0.07
    왔다
    -0.07
    莫过于
    -0.07
    esda
    -0.06
    ではありません
    -0.06
     pł
    -0.06
     개최
    -0.06
    궂
    -0.06
     savory
    -0.06
    Italian
    -0.06
    POSITIVE LOGITS
     Direction
    0.08
     XCTAssert
    0.07
    (Room
    0.07
    Risk
    0.07
     phi
    0.07
     aria
    0.07
    .phi
    0.07
     Website
    0.07
    -admin
    0.07
    RED
    0.07
    Act Density 0.001%

    No Known Activations