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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "the."

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

    time periods and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fillType
    -0.52
    ronpa
    -0.51
    ACHUSET
    -0.47
     destrucción
    -0.46
     Савезне
    -0.45
    denn
    -0.43
    ➌
    -0.43
    ocardio
    -0.42
    arakhand
    -0.42
     imprimée
    -0.42
    POSITIVE LOGITS
     throughout
    0.57
     during
    0.55
     weeks
    0.54
    ช่วง
    0.52
     periods
    0.50
     recent
    0.49
     period
    0.48
     week
    0.48
     протягом
    0.47
     summer
    0.47
    Act Density 0.035%

    No Known Activations