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

    Neuronpedia

    INDEX
    Explanations

    network congestion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bpy
    -0.09
     edible
    -0.09
     trif
    -0.09
     crime
    -0.09
     turnkey
    -0.08
     altar
    -0.08
     Taschen
    -0.08
    _blank
    -0.08
     perman
    -0.08
     Twig
    -0.08
    POSITIVE LOGITS
     retrans
    0.16
     congestion
    0.16
     thrott
    0.12
     resend
    0.12
     bitrate
    0.12
     retries
    0.11
    Bandwidth
    0.11
     pacing
    0.11
     bandwidth
    0.11
     congest
    0.11
    Act Density 0.005%

    No Known Activations