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

    Neuronpedia

    INDEX
    Explanations

    database connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grain
    0.77
     columnar
    0.77
     SQL
    0.74
     query
    0.73
    सीपी
    0.69
     transcript
    0.69
     plan
    0.68
     iron
    0.68
     queries
    0.67
     table
    0.67
    POSITIVE LOGITS
    Connect
    1.35
    connect
    1.32
    连接
    1.29
    Connecting
    1.28
     bağlant
    1.28
     conectar
    1.28
     Connect
    1.24
     连接
    1.23
     connect
    1.22
     Connecting
    1.20
    Act Density 0.087%

    No Known Activations