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

    Neuronpedia

    INDEX
    Explanations

    governance, decisions, wealth, status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iMac
    0.51
    мак
    0.49
    Сма
    0.47
    Фа
    0.45
     Гра
    0.45
    Due
    0.44
    లోకి
    0.44
     girly
    0.44
    Гра
    0.43
     iPhone
    0.42
    POSITIVE LOGITS
    efined
    0.49
     अमीर
    0.46
     नेता
    0.45
     samego
    0.44
     ধনী
    0.44
     توسعه
    0.43
    eweg
    0.43
     tanned
    0.41
     venda
    0.41
     تصمیم
    0.41
    Act Density 0.003%

    No Known Activations