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

    Neuronpedia

    INDEX
    Explanations

    descriptive texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    画
    -0.07
     Scalar
    -0.06
    ulist
    -0.06
     Latin
    -0.06
     scalar
    -0.06
    istance
    -0.06
     결혼
    -0.06
     copp
    -0.06
     jug
    -0.06
     긴
    -0.06
    POSITIVE LOGITS
     За
    0.07
     czę
    0.07
     Shotgun
    0.06
    eworld
    0.06
     XCTAssert
    0.06
     examines
    0.06
    LONG
    0.06
    reducers
    0.06
    -Con
    0.06
     отп
    0.06
    Act Density 0.649%

    No Known Activations