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

    Neuronpedia

    INDEX
    Explanations

    bridge and bridging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     פאר
    0.41
    쌍
    0.41
     Chains
    0.41
     נוס
    0.40
    დეს
    0.39
     së
    0.38
     ప్రా
    0.37
     ஜனநாயக
    0.37
     состо
    0.36
    ឺ
    0.36
    POSITIVE LOGITS
    Brid
    0.95
     bridging
    0.93
    brid
    0.88
     Brid
    0.85
     brid
    0.80
     bridged
    0.76
    BRID
    0.75
     bridge
    0.71
    Bridge
    0.69
     bridges
    0.64
    Act Density 0.004%

    No Known Activations