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

    Neuronpedia

    INDEX
    Explanations

    headings and section starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ซึ่ง
    0.42
    点了点头
    0.33
    <unused429>
    0.33
    larının
    0.31
    ซึ่ง
    0.31
    非常的
    0.31
    ễm
    0.30
    which
    0.30
    ংকের
    0.30
    <unused2204>
    0.30
    POSITIVE LOGITS
    </h2>
    0.40
     legjob
    0.34
    Ს
    0.34
    </h4>
    0.33
     OOP
    0.33
     a
    0.32
    ଡ
    0.32
     కానీ
    0.31
    以外
    0.31
     rohkem
    0.30
    Act Density 0.557%

    No Known Activations