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

    Neuronpedia

    INDEX
    Explanations

    references to cafe experiences and offerings

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

    food and drinks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nights
    -0.83
     Night
    -0.79
     gece
    -0.79
    IndentedString
    -0.74
     nightly
    -0.74
    Nights
    -0.74
    Night
    -0.73
     Tonight
    -0.72
    nights
    -0.71
    Tonight
    -0.69
    POSITIVE LOGITS
     cafe
    0.91
     coffee
    0.90
     café
    0.85
     pastries
    0.73
     cafes
    0.72
     coffees
    0.68
     latte
    0.68
     cakes
    0.67
     barista
    0.66
    coffee
    0.65
    Act Density 0.013%

    No Known Activations