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

    Neuronpedia

    INDEX
    Explanations

    address and contact information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     தரி
    0.42
    heits
    0.40
    pred
    0.39
     والخ
    0.39
    icha
    0.38
    Omn
    0.37
    率
    0.37
     اکبر
    0.36
     Omn
    0.36
    pie
    0.36
    POSITIVE LOGITS
     email
    0.63
     billing
    0.58
    Email
    0.57
     EMAIL
    0.57
     Email
    0.55
     ईमेल
    0.55
     Billing
    0.53
    email
    0.52
    EMAIL
    0.52
     mailing
    0.52
    Act Density 0.084%

    No Known Activations