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

    Neuronpedia

    INDEX
    Explanations

    encaps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    電
    -0.07
     Dmitry
    -0.07
     �
    -0.07
     severity
    -0.07
     dirs
    -0.07
     inspector
    -0.07
    政
    -0.07
    098
    -0.06
     struggles
    -0.06
    298
    -0.06
    POSITIVE LOGITS
     encompass
    0.10
     encompasses
    0.08
    ует
    0.07
     )↵↵
    0.06
    BP
    0.06
     Medicaid
    0.06
    uy�
    0.06
     высок
    0.06
    納
    0.06
    ﻤ
    0.06
    Act Density 0.009%

    No Known Activations