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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    in
    -0.08
    11
    -0.07
     Livingston
    -0.07
    ин
    -0.07
    ін
    -0.07
    }↵↵
    -0.07
    58
    -0.07
        ↵
    -0.07
    12
    -0.07
     jm
    -0.06
    POSITIVE LOGITS
     �
    0.07
     sä
    0.07
    보고
    0.07
    αρίου
    0.07
     hợp
    0.06
     igual
    0.06
    ！！
    0.06
    complexContent
    0.06
    เรา
    0.06
    [section
    0.06
    Act Density 0.095%

    No Known Activations