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

    Neuronpedia

    INDEX
    Explanations

    anticipatory and retrospective language indicating plans and memories

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

    restaurant and dining frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.51
     consultato
    -0.45
     surla
    -0.41
     ويكيپيديا
    -0.41
    र्शन
    -0.40
     Wissenschaften
    -0.39
     Taktlose
    -0.39
    expandindo
    -0.39
    󠁴
    -0.38
     informée
    -0.37
    POSITIVE LOGITS
     restaurant
    0.51
     Restaurant
    0.48
     frequ
    0.47
    Restaurant
    0.47
     frecu
    0.46
     frequented
    0.44
    restaurant
    0.44
     eatery
    0.42
     bike
    0.42
     takeout
    0.41
    Act Density 0.009%

    No Known Activations