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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kor
    -0.09
     ಯಾವುದೇ
    -0.08
     कुनै
    -0.08
    dan
    -0.08
     рад
    -0.08
     한국
    -0.08
    \">\
    -0.08
     नेपाल
    -0.08
     любого
    -0.07
     Nelson
    -0.07
    POSITIVE LOGITS
     etc
    0.14
    ...),
    0.11
    ,etc
    0.11
    等等
    0.10
     וכו
    0.10
     વગેરે
    0.10
     usw
    0.10
     ...↵↵
    0.10
     vs
    0.10
     ....↵↵
    0.10
    Act Density 0.058%

    No Known Activations