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

    Neuronpedia

    INDEX
    Explanations

    reply and communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تخص
    0.43
     актив
    0.42
    記録
    0.42
     علم
    0.41
     динами
    0.41
     arşiv
    0.40
     корре
    0.40
     كور
    0.38
    RECORD
    0.38
     дина
    0.38
    POSITIVE LOGITS
     Reply
    0.53
    reply
    0.51
     Skype
    0.50
     texting
    0.49
     Whatsapp
    0.49
     replying
    0.48
     email
    0.47
     reply
    0.47
     WhatsApp
    0.46
    Chat
    0.44
    Act Density 0.050%

    No Known Activations