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

    Neuronpedia

    INDEX
    Explanations

    linguistic terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @test
    -0.08
     jackets
    -0.07
    .TextChanged
    -0.07
    -proof
    -0.06
     "!
    -0.06
     diarrhea
    -0.06
    念
    -0.06
     Franz
    -0.06
    -none
    -0.06
     Expect
    -0.06
    POSITIVE LOGITS
    偶
    0.07
    resolution
    0.06
     hj
    0.06
    ottie
    0.06
     helf
    0.06
     secre
    0.06
    setFont
    0.06
     determinant
    0.06
    そこで
    0.06
    긷
    0.06
    Act Density 0.096%

    No Known Activations