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

    Neuronpedia

    INDEX
    Explanations

    government

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bewohner
    -0.08
     inwoners
    -0.08
     bewoners
    -0.08
     Verdict
    -0.08
     habitantes
    -0.08
    npm
    -0.08
     discours
    -0.08
     verdict
    -0.07
     habitants
    -0.07
     رسمی
    -0.07
    POSITIVE LOGITS
     bipartisan
    0.10
     modifying
    0.09
     provisions
    0.08
     sửa
    0.08
     protections
    0.08
     Medicare
    0.08
    _dbg
    0.08
     compassion
    0.08
     Madd
    0.08
     ಕಾಂಗ್ರೆಸ್
    0.08
    Act Density 0.072%

    No Known Activations