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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -icons
    -0.08
     одним
    -0.07
    Deep
    -0.07
    eries
    -0.06
    λει
    -0.06
     Betty
    -0.06
     вет
    -0.06
    Resolve
    -0.06
     任
    -0.06
     застосування
    -0.06
    POSITIVE LOGITS
    %",↵
    0.07
     Murdoch
    0.06
    />
↵
    0.06
    ":{↵
    0.06
    ｱ
    0.06
    하였
    0.06
    었
    0.06
    ﻴ
    0.06
     χα
    0.06
    ...↵
    0.06
    Act Density 0.002%

    No Known Activations