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

    Neuronpedia

    INDEX
    Explanations

    database table design/queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IRD
    -0.08
    Decimals
    -0.08
    allen
    -0.08
     hopes
    -0.08
    atzen
    -0.07
    财富
    -0.07
     sharp
    -0.07
     problems
    -0.07
     SO
    -0.07
     rechten
    -0.07
    POSITIVE LOGITS
    ุณ
    0.09
    garage
    0.08
     Manit
    0.08
     เวลา
    0.07
    gå
    0.07
    cam
    0.07
    ్డు
    0.07
     Georges
    0.07
     bipartisan
    0.07
    .set
    0.07
    Act Density 0.001%

    No Known Activations