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

    Neuronpedia

    INDEX
    Explanations

    Senate and political entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ى
    1.31
    м
    1.30
    ного
    1.11
    mě
    1.05
    م
    1.02
    ت
    0.99
    ة
    0.98
    ів
    0.98
    ,
    0.97
    ě
    0.93
    POSITIVE LOGITS
    O
    1.35
    '
    1.02
    ↵↵
    1.01
     Senate
    0.96
    </em>
    0.96
    ){
    0.96
    EG
    0.92
    )
    0.91
    OV
    0.91
    </strong>
    0.89
    Act Density 0.002%

    No Known Activations