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

    Neuronpedia

    INDEX
    Explanations

    space engineers servers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    律师
    0.43
    Dialogue
    0.41
    财政
    0.40
    主体
    0.40
     dialogue
    0.39
     canonical
    0.39
     ancillary
    0.39
     തിരഞ്ഞെടു
    0.39
     выборах
    0.38
     auxiliary
    0.38
    POSITIVE LOGITS
     Server
    0.67
     server
    0.64
    Server
    0.57
     servidor
    0.57
    サーバー
    0.55
    server
    0.54
     dinosaurs
    0.53
     Servers
    0.53
     dinosaur
    0.52
    服务器
    0.51
    Act Density 0.021%

    No Known Activations