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

    Neuronpedia

    INDEX
    Explanations

    pair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tomar
    -0.06
     yoktur
    -0.06
     الذه
    -0.06
     části
    -0.06
    ált
    -0.06
     cháy
    -0.06
    ्यकत
    -0.06
     �
    -0.06
    충
    -0.06
     sân
    -0.06
    POSITIVE LOGITS
    "]').
    0.07
    ้าร
    0.07
    (route
    0.06
    :\"
    0.06
    ]):
↵
    0.06
    "><?=$
    0.06
    ')).
    0.06
    ury
    0.06
    	device
    0.06
    '])[
    0.06
    Act Density 0.003%

    No Known Activations