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

    Neuronpedia

    INDEX
    Explanations

    the presence of a specific start token in the text

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

    Follows initial capital letter abbreviations

    np_acts-logits-general · gemini-2.0-flash

    Friday

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Monday
    -0.88
     Monday
    -0.88
     lundi
    -0.76
    MONDAY
    -0.74
     MONDAY
    -0.67
    Lundi
    -0.67
     monday
    -0.65
     lunedì
    -0.64
     Montag
    -0.64
     Mondays
    -0.61
    POSITIVE LOGITS
     Fridays
    0.82
     Friday
    0.80
    Friday
    0.75
     Fri
    0.73
    Fri
    0.72
     friday
    0.68
    friday
    0.66
     FRIDAY
    0.61
     viernes
    0.58
     venerdì
    0.57
    Act Density 0.049%

    No Known Activations