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

    Neuronpedia

    INDEX
    Explanations

    politics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Yet
    -0.07
     discs
    -0.07
     springs
    -0.07
     ASE
    -0.06
     Palace
    -0.06
     evidently
    -0.06
    .parse
    -0.06
    Preferences
    -0.06
     concluding
    -0.06
     Cyan
    -0.06
    POSITIVE LOGITS
    ]})↵
    0.06
     холодиль
    0.06
     Kota
    0.06
    енню
    0.06
     standby
    0.06
     thao
    0.06
    ystatechange
    0.06
     setups
    0.06
    ่าก
    0.06
     thrott
    0.06
    Act Density 0.048%

    No Known Activations