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

    Neuronpedia

    INDEX
    Explanations

    email address and mailing address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Staff
    0.66
    Motivation
    0.58
     staff
    0.57
    Reply
    0.57
    Photos
    0.57
    Insertion
    0.56
    Insert
    0.55
    Contacts
    0.53
    VIEW
    0.53
     réfé
    0.53
    POSITIVE LOGITS
    ︰
    0.98
    ∶
    0.96
    邮箱
    0.93
    ：
    0.88
    ៈ
    0.87
    :“
    0.84
     email
    0.83
     ईमेल
    0.83
     Email
    0.83
     correo
    0.82
    Act Density 0.013%

    No Known Activations