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

    Neuronpedia

    INDEX
    Explanations

    email addresses and domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '/
    0.39
     busts
    0.36
    arran
    0.35
     proximity
    0.35
    遥
    0.34
    銘
    0.34
    UMP
    0.34
    byter
    0.33
    <tbody>
    0.33
    rin
    0.33
    POSITIVE LOGITS
    Gmail
    0.82
     Gmail
    0.77
     gmail
    0.75
    gmail
    0.70
     Mail
    0.60
     mail
    0.57
     smtp
    0.57
    Mail
    0.55
    mail
    0.54
     domains
    0.54
    Act Density 0.011%

    No Known Activations