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

    Neuronpedia

    INDEX
    Explanations

    marketing calls to action

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

    phrasing and tokens that mark section headings or emphasized/structured formatting (e.g., bold markers, option/section titles, and similar layout cues).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     variations
    0.42
     generally
    0.40
     variability
    0.40
     variation
    0.40
     preferably
    0.40
     organism
    0.40
     substitution
    0.39
     overall
    0.39
     murid
    0.39
     এইরূপ
    0.38
    POSITIVE LOGITS
    Get
    0.98
    Discover
    0.89
    Learn
    0.88
     Get
    0.88
    Explore
    0.86
     discover
    0.84
    discover
    0.83
    Join
    0.81
    Enjoy
    0.80
     Discover
    0.80
    Act Density 0.043%

    No Known Activations