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

    Neuronpedia

    INDEX
    Explanations

    email addresses and IP addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    économie
    0.68
    낀
    0.67
     termo
    0.66
     লাভ
    0.65
    通道
    0.65
    Bienvenidos
    0.65
    మంలో
    0.64
     nivå
    0.64
     topik
    0.63
     kereta
    0.63
    POSITIVE LOGITS
     address
    2.08
     addresses
    2.07
     Address
    1.93
    address
    1.90
    Address
    1.88
     Addresses
    1.83
    Addresses
    1.78
    addresses
    1.75
     addr
    1.72
    地址
    1.66
    Act Density 0.454%

    No Known Activations