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

    Neuronpedia

    INDEX
    Explanations

    network devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VPN
    0.42
     VPN
    0.42
     Destination
    0.41
     destination
    0.40
     REMOTE
    0.39
    destination
    0.38
     port
    0.38
     remote
    0.38
     bundle
    0.38
    bundle
    0.37
    POSITIVE LOGITS
     مشار
    0.44
     Drinks
    0.44
     humanist
    0.44
    繭
    0.44
     DBox
    0.44
     assigns
    0.43
    痱
    0.42
     participating
    0.42
     membros
    0.42
    筊
    0.42
    Act Density 0.035%

    No Known Activations