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

    Neuronpedia

    INDEX
    Explanations

    AI prompts, alignment, answering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     celebration
    0.98
     music
    0.87
     передви
    0.87
     celebrations
    0.87
    eltic
    0.83
     festivities
    0.83
     sculpture
    0.80
     musicians
    0.80
     brotherhood
    0.80
    न्ध
    0.79
    POSITIVE LOGITS
     OpenAI
    1.80
     ChatGPT
    1.74
    ChatGPT
    1.54
     hyperparameters
    1.45
     embeddings
    1.30
     prompts
    1.29
     chatbot
    1.27
     cognit
    1.27
     openai
    1.26
     GPT
    1.25
    Act Density 1.939%

    No Known Activations