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

    Neuronpedia

    INDEX
    Explanations

    technical terms and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कहें
    0.39
     राजनीतिक
    0.38
    勰
    0.38
     eğer
    0.38
    Если
    0.38
    uza
    0.37
    肥料
    0.37
     জবাবে
    0.37
     драматур
    0.36
    <unused408>
    0.36
    POSITIVE LOGITS
    ↵↵
    0.43
     I
    0.42
    0.41
     B
    0.40
    :
    0.39
    ).
    0.38
    ↵
    0.38
    )
    0.38
    .
    0.38
     significantly
    0.37
    Act Density 0.097%

    No Known Activations