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

    Neuronpedia

    INDEX
    Explanations

    references to events or themes occurring during the current year

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

    this year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     today
    -0.94
     nowadays
    -0.89
     hoje
    -0.81
     aujourd
    -0.79
    today
    -0.78
     dziś
    -0.77
     oggi
    -0.76
     heute
    -0.75
     сегодня
    -0.75
     obecnie
    -0.73
    POSITIVE LOGITS
     particularly
    0.66
    +#+#
    0.66
     theme
    0.66
    particularly
    0.62
     especially
    0.60
    Again
    0.59
     Particularly
    0.59
     again
    0.59
     AGAIN
    0.58
     THEME
    0.57
    Act Density 0.030%

    No Known Activations