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

    Neuronpedia

    INDEX
    Explanations

    city names and news organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     实现
    0.42
    celikle
    0.40
     Basically
    0.40
    বারেই
    0.40
    Basically
    0.38
    本质
    0.38
    这将
    0.38
     selectedCard
    0.37
     Essentially
    0.36
     differentiating
    0.36
    POSITIVE LOGITS
    WASHINGTON
    0.58
    BOSTON
    0.57
     LONDON
    0.56
    Minneapolis
    0.55
    London
    0.52
     WASHINGTON
    0.52
    CHICAGO
    0.51
    Brussels
    0.51
    LONDON
    0.50
    Reuters
    0.49
    Act Density 0.003%

    No Known Activations