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

    Neuronpedia

    INDEX
    Explanations

    Executive Summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pecahan
    0.45
     duvar
    0.45
    zechoslovak
    0.42
    铀
    0.41
     paroi
    0.41
    attoo
    0.40
     treatises
    0.40
    個月
    0.40
    蓍
    0.40
    ■
    0.39
    POSITIVE LOGITS
     Emails
    0.46
     SWOT
    0.45
     Packer
    0.44
     Microsoft
    0.42
     Word
    0.42
    Offline
    0.42
    docx
    0.41
     KPIs
    0.41
     скри
    0.41
    0.41
    Act Density 0.005%

    No Known Activations