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

    Neuronpedia

    INDEX
    Explanations

    references to specific research studies or scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by bullet points, numbers, or symbols

    np_acts-logits-general · gemini-2.0-flash

    ElevationCOGNiko

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.08
    tagHelperRunner
    -1.08
    تقاوى
    -1.02
     increí
    -1.00
    Diwedd
    -0.99
    хьтан
    -0.98
    ſehen
    -0.98
     indígen
    -0.98
    iſchen
    -0.98
    ésultats
    -0.97
    POSITIVE LOGITS
     
    0.41
     &
    0.36
    &
    0.31
    The
    0.29
     D
    0.28
    U
    0.28
    0.27
     The
    0.27
    _
    0.26
    D
    0.26
    Act Density 0.975%

    No Known Activations