Update README.md

README.md

@@ -36,7 +36,8 @@ language:
 
 <img src="deadpan-savant.gif" style="float:right; width:300px; height:300px; padding:10px;">
 
-Savant Commander is a specialized MOE model that allows you to control which expert(s) are assigned to your use case(s) / prompt(s).
+Savant Commander is a specialized MOE model that allows you to control which expert(s) are assigned to your use case(s) / prompt(s) ...
+directly (by name(s)), as opposed to having the "choices" made for you.
 
 The model is composed of 12 DISTILLS (compressed 12x4B MOE) of top closed (GPT5.1, OpenAI 120 GPT Oss, Gemini (3), Claude (2) ) 
 and open source models (Kimi, GLM, Deepseek, Command-A, Jan) all in one.
@@ -81,15 +82,27 @@ Note the name[s] must be in the prompt and/or the system role and can be located
 
 For best results suggest using the name(s) at the beginning as a "command" / "request" :
 
-
 GLM do ...
 
 Using Gemini process this prompt:
 
-However, using the name[s] in the prompt will work in most cases as that is what is being "scanned for" during gating.
+However, using the name[s] in the prompt will work in most cases as that is what is being "scanned for" during "prompt processing".
+
+This model also has NEGATIVE gating to ensure other models not in use are ISOLATED.
 
 You MAY want to increase the number of active experts in some cases.
 
+For trying the model out (example):
+
+NAME, Tell me a horror story.
+
+Use a different "name" per "new chat" - you will get different thought blocks, output etc etc - in some cases very different
+from each other.
+
+SUGGESTED SETTINGS to START:
+
+Temp .7, topk 40, top p .95, min p .05, rep pen 1.05,
+
 <B>IMPORTANT: </B>
 
 - Min Quant of Q4ks (non imatrix) or IQ3_M (imatrix) ; otherwise it will "snap".