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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    άνω
    -0.07
    _heap
    -0.07
    _unused
    -0.06
     восп
    -0.06
     пер
    -0.06
     happiest
    -0.06
     pouze
    -0.06
    nem
    -0.06
    投注
    -0.06
    filled
    -0.06
    POSITIVE LOGITS
     Ging
    0.07
     برنامه
    0.06
     bridal
    0.06
     Boss
    0.06
     verify
    0.06
     XCTAssertTrue
    0.06
    。“
    0.06
     Verify
    0.06
     Vick
    0.06
     generalized
    0.06
    Act Density 0.013%

    No Known Activations