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

    Neuronpedia

    INDEX
    Explanations

    AI tutor and chatbot explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    testAvg
    0.50
    Strafpunkte
    0.42
     testes
    0.41
    夰
    0.40
    फरी
    0.40
     restitu
    0.40
    branchNode
    0.40
    avatth
    0.39
    軼
    0.39
     число
    0.39
    POSITIVE LOGITS
     Assistant
    0.53
     OpenAI
    0.48
     Session
    0.46
     Chat
    0.45
     Assistants
    0.45
     Echo
    0.44
     Open
    0.43
     Conversation
    0.43
     assistant
    0.42
    openai
    0.42
    Act Density 0.001%

    No Known Activations