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

    Neuronpedia

    INDEX
    Explanations

    living and dining areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.73
    Ç
    0.69
    Ü
    0.68
    Укра
    0.65
    XI
    0.64
    Мен
    0.62
    挖掘
    0.61
    发布
    0.61
    Ş
    0.61
    博士
    0.60
    POSITIVE LOGITS
     dining
    0.84
    ка
    0.76
    dining
    0.76
     comedor
    0.75
    ين
    0.74
    та
    0.70
    мо
    0.69
     FGD
    0.69
     リビング
    0.67
     Dining
    0.66
    Act Density 0.008%

    No Known Activations