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

    Neuronpedia

    INDEX
    Explanations

    ring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CO
    -0.07
     BC
    -0.07
    cool
    -0.06
     자유
    -0.06
    	ST
    -0.06
    Care
    -0.06
     chocol
    -0.06
     Dispose
    -0.06
     sulla
    -0.06
     Hou
    -0.06
    POSITIVE LOGITS
     ring
    0.13
     rings
    0.11
     Ring
    0.10
    Ring
    0.09
     Rings
    0.09
    Existing
    0.08
    -ring
    0.08
    řen
    0.08
          
↵
    0.08
     
↵ 
↵
    0.07
    Act Density 0.009%

    No Known Activations