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

    Neuronpedia

    INDEX
    Explanations

    .Okay

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

    explicit task instructions and formatting constraints in prompts, especially colon-introduced sections and output requirements.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     nutritive
    0.30
     hadrons
    0.30
     mesons
    0.30
     lathes
    0.30
     implants
    0.30
     radiographs
    0.29
     lymphocytes
    0.29
     emulsions
    0.29
     bilayers
    0.29
     cafeteria
    0.29
    POSITIVE LOGITS
    and
    0.36
    then
    0.33
     તથા
    0.33
    or
    0.32
     Voici
    0.32
    und
    0.32
    ouncing
    0.32
    that
    0.32
    have
    0.32
     voici
    0.32
    Act Density 0.742%

    No Known Activations