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

    Neuronpedia

    INDEX
    Explanations

    AI chatbot disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    faulse
    0.40
     SPE
    0.37
     gql
    0.37
     وقع
    0.36
     SCE
    0.36
    ⵓ
    0.36
     focal
    0.35
    Nina
    0.35
    交往
    0.35
    頖
    0.35
    POSITIVE LOGITS
     chatbot
    0.54
    chatbot
    0.49
     bots
    0.41
     Bots
    0.40
    GPT
    0.39
    bot
    0.38
    Contents
    0.37
    Jasper
    0.37
     bot
    0.37
     chatbots
    0.37
    Act Density 0.018%

    No Known Activations