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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe social interactions and experiences

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

    Followed by a verb of motion

    np_acts-logits-general · gemini-2.0-flash

    travel to places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monthly
    -0.67
     weeks
    -0.63
     wöch
    -0.63
    olism
    -0.62
    每月
    -0.61
     weekends
    -0.61
     helg
    -0.60
    Weekly
    -0.60
    verket
    -0.60
     month
    -0.59
    POSITIVE LOGITS
     lunch
    0.83
     wandered
    0.76
     headed
    0.70
     strolled
    0.68
     exploring
    0.68
     dinner
    0.67
     strolling
    0.66
     wandering
    0.66
     freshen
    0.66
     stroll
    0.65
    Act Density 0.192%

    No Known Activations