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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     znovu
    -0.07
     서버
    -0.06
    layout
    -0.06
    _register
    -0.06
    .layouts
    -0.06
    prs
    -0.06
     pow
    -0.06
    \t
    -0.06
    ('//
    -0.06
    liness
    -0.06
    POSITIVE LOGITS
     대구
    0.07
    感じ
    0.06
     بعض
    0.06
     disappearing
    0.06
    осков
    0.06
     울
    0.06
    σφα
    0.06
     yaptık
    0.06
                       ↵
    0.06
    ευση
    0.06
    Act Density 0.014%

    No Known Activations