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

    Neuronpedia

    INDEX
    Explanations

    references to the "highest" levels or standards in various contexts

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

    highest common factor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulemon
    -0.51
     bunnies
    -0.48
     pickles
    -0.47
     algodão
    -0.46
     MERCHANTABILITY
    -0.46
    Algérie
    -0.45
    ofday
    -0.45
     sandwiches
    -0.45
     Tread
    -0.45
    Rüyada
    -0.45
    POSITIVE LOGITS
     highest
    2.08
    highest
    1.86
     Highest
    1.85
    Highest
    1.82
     höchste
    1.23
     tertinggi
    1.23
     höchsten
    1.19
     lowest
    1.13
     Lowest
    1.10
    Lowest
    1.09
    Act Density 0.009%

    No Known Activations