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

    Neuronpedia

    INDEX
    Explanations

    Direct address to reader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resumed
    -0.07
    OutOfRange
    -0.06
    	If
    -0.06
     Sandra
    -0.06
     cst
    -0.06
    [block
    -0.06
     ChatColor
    -0.06
     aşağıdaki
    -0.06
    Taken
    -0.06
     sees
    -0.06
    POSITIVE LOGITS
     прежде
    0.07
     evenly
    0.07
     Wealth
    0.07
    
    0.06
     neler
    0.06
     özelliği
    0.06
    ');↵↵
    0.06
    нож
    0.06
     suche
    0.06
     sizing
    0.06
    Act Density 0.014%

    No Known Activations