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

    Neuronpedia

    INDEX
    Explanations

    rubbing and related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )
    -2.45
     neue
    -2.44
    The
    -2.44
    ve
    -2.34
    -2.33
    -2.30
    T
    -2.28
    我们
    -2.22
    小時
    -2.22
    J
    -2.20
    POSITIVE LOGITS
    耵
    2.73
    FirstName
    2.48
    鷓
    2.31
    嫱
    2.28
    蹕
    2.28
    絎
    2.25
    睺
    2.19
    妧
    2.06
    »;
    2.05
    硨
    2.05
    Act Density 0.014%

    No Known Activations