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

    Neuronpedia

    INDEX
    Explanations

    policy/politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bfd
    -0.07
     например
    -0.07
     світі
    -0.07
    protocols
    -0.06
     дво
    -0.06
     rights
    -0.06
    vendor
    -0.06
    agy
    -0.06
    primitive
    -0.06
    ／↵
    -0.06
    POSITIVE LOGITS
     policy
    0.10
     Policy
    0.08
     policies
    0.07
     Desired
    0.07
     HTML
    0.07
     Procedure
    0.06
     Policies
    0.06
    ORAGE
    0.06
    .choices
    0.06
    .ADMIN
    0.06
    Act Density 0.032%

    No Known Activations