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

    Neuronpedia

    INDEX
    Explanations

    cover letter requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ுள்ளனர்
    0.46
     playoffs
    0.41
     quotas
    0.39
     rankings
    0.39
     billboards
    0.39
     spam
    0.38
     наших
    0.38
    branded
    0.38
     recruiters
    0.38
     impost
    0.38
    POSITIVE LOGITS
     Cover
    0.89
     cover
    0.86
    Cover
    0.79
    cover
    0.77
     letter
    0.77
     Letter
    0.73
    カバー
    0.70
    COVER
    0.69
     कवर
    0.69
     lettre
    0.69
    Act Density 0.012%

    No Known Activations