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

    Neuronpedia

    INDEX
    Explanations

    Technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resembl
    -0.08
    (FLAGS
    -0.07
     =>
↵
    -0.07
    ість
    -0.06
     runApp
    -0.06
     czy
    -0.06
    		
↵		
↵
    -0.06
     Що
    -0.06
    ,’’
    -0.06
     fChain
    -0.06
    POSITIVE LOGITS
    implify
    0.06
     manager
    0.06
     문의
    0.06
    Absolutely
    0.06
     Elliott
    0.06
    ricula
    0.06
    ابي
    0.06
    John
    0.06
     PCS
    0.06
    DS
    0.06
    Act Density 0.000%

    No Known Activations