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

    Neuronpedia

    INDEX
    Explanations

    discussions around media biases and their impacts on perception

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

    after "the media"

    np_acts-logits-general · gemini-2.0-flash

    automatically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.79
    NameInMap
    -0.69
    webElementXpaths
    -0.64
     }{@
    -0.59
     ExecuteAsync
    -0.58
     ivelany
    -0.56
     Meksiku
    -0.55
     cherchés
    -0.55
    Хьажоргаш
    -0.55
    SharedDtor
    -0.54
    POSITIVE LOGITS
     automatiquement
    0.81
     automatically
    0.79
     automáticamente
    0.74
     automaticamente
    0.70
    ówczas
    0.68
    automatically
    0.66
     obligatoire
    0.64
     AUTOMATIC
    0.62
     automatisch
    0.61
     Automatically
    0.61
    Act Density 0.669%

    No Known Activations