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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     callers
    0.41
     caller
    0.39
     betrayal
    0.38
     nipple
    0.38
    ренные
    0.38
     blobs
    0.37
    -//
    0.36
    ANEOUS
    0.36
    拶
    0.36
     fillets
    0.36
    POSITIVE LOGITS
     email
    1.07
    email
    1.04
     john
    0.96
     Email
    0.93
    Email
    0.91
    mailto
    0.90
    邮箱
    0.89
     david
    0.89
     ईमेल
    0.86
    john
    0.82
    Act Density 0.025%

    No Known Activations