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

    Neuronpedia

    INDEX
    Explanations

    Reviews or Titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تمر
    -0.07
    聚
    -0.06
     tras
    -0.06
     Dry
    -0.06
     receipt
    -0.06
     typical
    -0.06
     changed
    -0.06
     consultar
    -0.06
    匹
    -0.06
     البر
    -0.06
    POSITIVE LOGITS
    //------------------------------------------------------------------------------↵↵
    0.08
    isEqual
    0.07
    ihad
    0.07
    ."&
    0.06
    	go
    0.06
    isiyle
    0.06
    .He
    0.06
     tộc
    0.06
     Dış
    0.06
     firm
    0.06
    Act Density 0.180%

    No Known Activations