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

    Neuronpedia

    INDEX
    Explanations

    mathematical constructs and symbols related to functions and transformations

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

    Followed by "then"

    np_acts-logits-general · gemini-2.0-flash

    punctuation or symbols then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exacts
    -0.67
     Lordships
    -0.67
    ことができました
    -0.62
    iastes
    -0.61
    Espèce
    -0.60
    kloped
    -0.60
    Hauptartikel
    -0.56
    ともに
    -0.55
     cherchés
    -0.54
    selves
    -0.54
    POSITIVE LOGITS
     then
    3.90
    then
    3.00
     Then
    2.90
    Then
    2.87
     entonces
    2.76
     THEN
    2.62
     allora
    2.60
     então
    2.52
    THEN
    2.32
     dann
    2.29
    Act Density 1.159%

    No Known Activations