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

    Neuronpedia

    INDEX
    Explanations

    online chat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perse
    0.41
     biosynthesis
    0.39
    آمد
    0.38
     étamines
    0.38
    䀨
    0.38
     SPINE
    0.38
     }}{\
    0.37
     récol
    0.37
    емая
    0.36
     sutures
    0.36
    POSITIVE LOGITS
     chatting
    0.86
     Chat
    0.85
    Chat
    0.83
     chat
    0.82
     chats
    0.80
     chatted
    0.77
    chat
    0.74
    聊天
    0.73
     चैट
    0.71
     Chats
    0.68
    Act Density 0.000%

    No Known Activations