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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ependency
    -0.07
     aun
    -0.07
     literal
    -0.06
     kul
    -0.06
     swell
    -0.06
     Guantanamo
    -0.06
    ulture
    -0.06
     Abbas
    -0.06
     приня
    -0.06
    -social
    -0.06
    POSITIVE LOGITS
    }\\
    0.06
    ۷
    0.06
     ecosystems
    0.06
     date
    0.06
     Assertions
    0.06
     createDate
    0.06
    |↵↵
    0.06
    ्तक
    0.06
     \\
    0.06
     Dedicated
    0.06
    Act Density 0.000%

    No Known Activations