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

    Neuronpedia

    INDEX
    Explanations

    specific keywords followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ם
    0.43
     Planning
    0.42
    אם
    0.42
     Carolina
    0.41
     झु
    0.40
    ँसी
    0.39
    σί
    0.39
    ן
    0.39
     Warehouse
    0.39
    够
    0.39
    POSITIVE LOGITS
     .\
    0.49
    Ƹ
    0.45
    zeitig
    0.45
     CONTRIBUTORS
    0.44
    唋
    0.44
     よ
    0.44
     آزاد
    0.43
     лигасы
    0.43
    ('\\
    0.43
     dritte
    0.43
    Act Density 0.001%

    No Known Activations