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

    Neuronpedia

    INDEX
    Explanations

    references to zoos or zoo-related topics

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

    zoo and zoomed variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gerhard
    -0.56
    WriteTagHelper
    -0.50
     Edwards
    -0.50
     TSI
    -0.50
    Erik
    -0.50
     Martin
    -0.48
    RIEL
    -0.48
    Felipe
    -0.47
     Graham
    -0.47
     Erik
    -0.47
    POSITIVE LOGITS
     Zoo
    2.33
     zoo
    2.31
    Zoo
    2.30
    zoo
    1.99
     zoos
    1.59
     Zoological
    1.39
     Zoology
    1.20
    動物園
    1.09
    zookeeper
    1.06
     Zool
    1.02
    Act Density 0.001%

    No Known Activations