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

    Neuronpedia

    INDEX
    Explanations

    temporal references and expressions of time elapsed

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

    weeks ago

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     giuri
    -0.56
    几年
    -0.56
    每年
    -0.54
     anuales
    -0.53
     åren
    -0.52
    Years
    -0.52
     yearly
    -0.52
    Yearly
    -0.52
     Jahre
    -0.51
     talentos
    -0.51
    POSITIVE LOGITS
     week
    0.81
     Week
    0.66
     weeks
    0.65
    findpost
    0.59
    week
    0.59
     weekend
    0.58
    Week
    0.55
     WEEK
    0.55
     Monday
    0.53
     Weeks
    0.53
    Act Density 0.022%

    No Known Activations