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

    Neuronpedia

    INDEX
    Explanations

    Windows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Accountability
    -0.07
    .attr
    -0.06
    Candidate
    -0.06
     Haut
    -0.06
     đột
    -0.06
     HashMap
    -0.06
     Nurses
    -0.06
     Gaga
    -0.06
    ाध
    -0.06
     brig
    -0.06
    POSITIVE LOGITS
     Windows
    0.07
    Work
    0.06
    	exit
    0.06
    Veter
    0.06
    ＜
    0.06
     Winds
    0.06
     bridal
    0.06
    �
    0.06
    	RETURN
    0.06
      
    0.06
    Act Density 0.008%

    No Known Activations