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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "second" in various contexts

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

    Ordinal numbers (second, third)

    np_acts-logits-general · gemini-2.0-flash

    second plus common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.69
     Theſe
    -0.67
    MessageTagHelper
    -0.64
    ksikon
    -0.64
    abestanden
    -0.62
    either
    -0.60
     Gazetteer
    -0.60
     quiera
    -0.57
    脚注の使い方
    -0.56
     diyor
    -0.55
    POSITIVE LOGITS
    arily
    0.92
     Third
    0.92
    Third
    0.86
     Second
    0.85
    aries
    0.79
     THIRD
    0.79
     SECOND
    0.74
     third
    0.72
    Second
    0.70
    SECOND
    0.69
    Act Density 0.181%

    No Known Activations