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

    Neuronpedia

    INDEX
    Explanations

    what it returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ލ
    0.38
    역
    0.37
     શહેર
    0.36
    лера
    0.36
     Repeating
    0.35
    Celebrating
    0.35
    섭
    0.34
    Repeating
    0.34
     അ
    0.33
    дек
    0.33
    POSITIVE LOGITS
     return
    2.23
     returns
    2.08
     returned
    2.06
    返回
    1.99
     返回
    1.96
     returning
    1.91
     возвра
    1.89
    return
    1.86
    returns
    1.85
     Returns
    1.81
    Act Density 0.037%

    No Known Activations