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

    Neuronpedia

    INDEX
    Explanations

    next, continuation, consecutive

    np_acts-logits-general · gemini-2.5-flash-lite

    directive and meta-instructional scaffolding in chat-style prompts, especially role/format tags, command markup, and structured response templates indicating how to answer.

    oai_token-act-pair · gpt-5Triggered by @irajjmoradi
    New Auto-Interp
    Negative Logits
     sache
    0.85
     används
    0.80
     SMD
    0.79
    κρι
    0.77
     métall
    0.75
     overstated
    0.74
     zowel
    0.73
     HD
    0.73
     ochron
    0.72
     bescherm
    0.72
    POSITIVE LOGITS
     next
    1.26
    next
    1.20
     consecutive
    1.13
     consecutively
    1.09
     continuation
    1.07
     continuing
    1.06
    Next
    1.06
     नेक्स्ट
    1.02
     successively
    1.01
     successive
    1.01
    Act Density 2.694%

    No Known Activations