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

    Neuronpedia

    INDEX
    Explanations

    voting in politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ח
    0.40
     चुनावी
    0.40
    jeu
    0.38
    ร
    0.37
    Rev
    0.36
    exceptions
    0.36
    Б
    0.36
    գ
    0.36
    ham
    0.36
    ㄴ
    0.36
    POSITIVE LOGITS
     votos
    0.47
    Shares
    0.45
    셰
    0.44
     ROUILLER
    0.43
     cast
    0.43
     Shares
    0.43
     AGAINST
    0.43
     paff
    0.42
     chàng
    0.42
     بالأ
    0.41
    Act Density 0.002%

    No Known Activations