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

    Neuronpedia

    INDEX
    Explanations

    and,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	 ↵
    -0.08
    	    ↵
    -0.07
    	  ↵
    -0.07
     lith
    -0.07
     licensee
    -0.07
    ↵ ↵
    -0.06
     LayoutInflater
    -0.06
    क
    -0.06
    تبة
    -0.06
    italic
    -0.06
    POSITIVE LOGITS
     He
    0.07
     NGX
    0.06
    .ByteString
    0.06
    edio
    0.06
     Cl
    0.06
     Việt
    0.06
     Bà
    0.06
    /archive
    0.06
    activ
    0.06
    Wal
    0.06
    Act Density 0.018%

    No Known Activations