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

    Neuronpedia

    INDEX
    Explanations

    elements related to rankings and status in sports or athletic contexts

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

    Tokens before/after capitalized names

    np_acts-logits-general · gemini-2.0-flash

    surnames and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -1.08
     Reſ
    -1.07
     purpoſe
    -1.06
     Houſe
    -1.04
     Majefty
    -1.03
     pleaſure
    -1.03
     houſe
    -1.03
     Diſ
    -1.03
     ſche
    -1.02
     ſmall
    -1.02
    POSITIVE LOGITS
     Johnson
    0.68
     Mc
    0.67
     van
    0.67
     von
    0.66
     Williams
    0.66
     Smith
    0.65
     Jones
    0.62
     de
    0.60
     Davis
    0.60
     Lee
    0.58
    Act Density 1.994%

    No Known Activations