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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を行い
    -1.78
    ごとの
    -1.68
    向けの
    -1.61
    様な
    -1.53
    .
    -1.49
    を実施
    -1.47
    €“
    -1.45
    ところに
    -1.45
    うわ
    -1.41
    ようです
    -1.38
    POSITIVE LOGITS
     as
    1.44
     also
    1.34
    や
    1.31
     will
    1.27
    <bos>
    1.27
    تحميل
    1.25
     may
    1.25
    獗
    1.23
    參考文獻
    1.23
    謁
    1.22
    Act Density 0.080%

    No Known Activations