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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nj
    -0.07
    cilik
    -0.07
     ethernet
    -0.06
     wich
    -0.06
     cyan
    -0.06
    spam
    -0.06
     LinearLayoutManager
    -0.06
     mov
    -0.06
    (range
    -0.06
     vacc
    -0.06
    POSITIVE LOGITS
     before
    0.15
    before
    0.11
     Before
    0.08
     avant
    0.08
    借
    0.07
    LCD
    0.07
    的地
    0.07
     BEFORE
    0.06
    	before
    0.06
     antes
    0.06
    Act Density 0.017%

    No Known Activations