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

    Neuronpedia

    INDEX
    Explanations

    bridge and spanning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.77
    gifts
    0.72
    a
    0.71
    p
    0.71
    es
    0.71
    balls
    0.68
    dirt
    0.68
    ak
    0.67
    boxes
    0.66
    ceans
    0.65
    POSITIVE LOGITS
     Bridge
    1.00
     bridge
    0.94
     I
    0.88
    桥
    0.83
     BRIDGE
    0.82
    橋
    0.74
     bridges
    0.66
     Bridges
    0.63
     সেতুর
    0.63
    Bridge
    0.63
    Act Density 0.003%

    No Known Activations