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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "up" in various contexts

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

    moving up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ervan
    -0.40
     mes
    -0.39
    InjectAttribute
    -0.37
     Soria
    -0.37
    })));
    -0.37
    routeProvider
    -0.36
    modelBuilder
    -0.35
    mes
    -0.34
     kształ
    -0.34
     daran
    -0.34
    POSITIVE LOGITS
     الرياضيه
    0.65
    Ranked
    0.56
     pinulongan
    0.55
     Walkover
    0.55
     upward
    0.54
    URLException
    0.52
     GenerationType
    0.52
     Ranked
    0.52
    Rank
    0.52
    Ranking
    0.51
    Act Density 0.006%

    No Known Activations