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

    Neuronpedia

    INDEX
    Explanations

    resources that await

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conversation
    1.08
     Conversation
    1.02
    Conversation
    0.97
     referral
    0.96
     communication
    0.92
     chatbot
    0.90
     verbal
    0.89
     Referral
    0.89
     contacted
    0.89
     contacting
    0.88
    POSITIVE LOGITS
     awaits
    1.71
     await
    1.50
     waiting
    1.49
     awaiting
    1.40
    await
    1.38
    waiting
    1.33
     awaited
    1.31
     waits
    1.27
    等待
    1.25
     menunggu
    1.23
    Act Density 0.528%

    No Known Activations