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

    Neuronpedia

    INDEX
    Explanations

    references to product classes and categories in documentation

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

    economy class travel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.57
    MessageOf
    -0.36
     Lernen
    -0.36
     spolup
    -0.35
     tâches
    -0.35
     aprender
    -0.35
    owań
    -0.34
     imparare
    -0.34
     myš
    -0.34
     coleção
    -0.33
    POSITIVE LOGITS
     class
    0.90
     economy
    0.86
     Economy
    0.85
     Class
    0.85
     classe
    0.83
     kelas
    0.78
    class
    0.77
    Class
    0.76
     clase
    0.73
    economy
    0.73
    Act Density 0.014%

    No Known Activations