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

    Neuronpedia

    INDEX
    Explanations

    citizen militias

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    st
    0.98
    d
    0.96
    p
    0.89
    r
    0.85
    ne
    0.84
    dail
    0.79
    dle
    0.77
    dı
    0.76
    dag
    0.75
    the
    0.75
    POSITIVE LOGITS
     militias
    1.16
    ↵↵
    1.15
     militia
    1.05
    </td>
    0.88
    的行为
    0.84
     Militia
    0.84
     not
    0.82
    ↵↵↵
    0.81
    ’
    0.81
    אם
    0.79
    Act Density 0.002%

    No Known Activations