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

    Neuronpedia

    INDEX
    Explanations

    election outcomes and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    로
    1.16
    ется
    1.12
    ۴
    1.09
    ۳
    1.02
    ור
    0.98
    ৫
    0.96
    ளும்
    0.94
    ۵
    0.93
    ના
    0.92
    ет
    0.92
    POSITIVE LOGITS
    0
    1.34
     Elections
    1.07
     elections
    0.94
     Election
    0.88
    th
    0.88
    ↵↵
    0.82
    pm
    0.80
    Election
    0.80
    goers
    0.79
    is
    0.78
    Act Density 0.004%

    No Known Activations