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

    Neuronpedia

    INDEX
    Explanations

    product categories and navigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </td>
    0.51
    -
    0.49
    平均
    0.48
    {}
    0.43
    0.43
    “-
    0.42
    注意
    0.42
    чої
    0.41
    的文件
    0.41
     obtainable
    0.41
    POSITIVE LOGITS
     Home
    0.54
     home
    0.49
     News
    0.47
     meus
    0.47
    Publications
    0.45
     Integrative
    0.45
     პარ
    0.43
     PUBLICATIONS
    0.43
     svůj
    0.43
     Leadership
    0.43
    Act Density 0.005%

    No Known Activations