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

    Neuronpedia

    INDEX
    Explanations

    email communications and messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jara
    0.82
     Piaget
    0.74
    ثار
    0.72
    ▔
    0.70
    ઘ
    0.69
    verbal
    0.69
    swagger
    0.69
     Joc
    0.68
    quilibrium
    0.68
     verbal
    0.68
    POSITIVE LOGITS
     email
    2.48
     Email
    2.41
    Email
    2.36
     mail
    2.32
     Mail
    2.30
     emails
    2.27
    Mail
    2.23
    mail
    2.21
     Emails
    2.08
    email
    2.07
    Act Density 0.621%

    No Known Activations