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

    Neuronpedia

    INDEX
    Explanations

    Gemma architecture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nomenclature
    0.69
     batsmen
    0.69
     Rawlings
    0.68
     epidemic
    0.66
     رجسٹ
    0.66
     NACA
    0.65
     গেরিলা
    0.65
    getFullYear
    0.64
     fans
    0.64
     branchNode
    0.63
    POSITIVE LOGITS
     ChatGPT
    1.78
    ChatGPT
    1.71
     GPT
    1.68
     OpenAI
    1.68
    GPT
    1.62
     prompt
    1.56
    Prompt
    1.55
     chat
    1.55
     prompts
    1.54
     Chat
    1.54
    Act Density 2.865%

    No Known Activations