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

    Neuronpedia

    INDEX
    Explanations

    servers and server racks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wörter
    0.47
     Steam
    0.42
     Diffusion
    0.42
     التف
    0.41
    凃
    0.41
    疠
    0.41
     Gameplay
    0.41
    ذف
    0.40
    幼児
    0.40
     steamer
    0.39
    POSITIVE LOGITS
     server
    1.20
    Server
    1.15
     servers
    1.13
     Server
    1.08
    server
    1.07
     서버
    1.07
     Servers
    1.04
     Xeon
    1.02
     сервер
    1.02
    servers
    1.00
    Act Density 0.048%

    No Known Activations