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

    Neuronpedia

    INDEX
    Explanations

    copy file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hải
    0.79
    Pension
    0.76
     Medicaid
    0.74
     Pension
    0.73
     অ্যাম
    0.72
     Nurse
    0.71
     कृष्णा
    0.71
     Schultz
    0.70
     Pensions
    0.70
     Ephesians
    0.69
    POSITIVE LOGITS
     files
    2.47
     file
    2.41
     Files
    2.23
    文件
    2.18
     File
    2.13
    ファイル
    2.13
    File
    2.11
     ファイル
    2.11
    files
    2.09
    file
    2.04
    Act Density 0.654%

    No Known Activations