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

    Neuronpedia

    INDEX
    Explanations

    prepositions that indicate direction or movement

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

    Follows prepositions or numbers

    np_acts-logits-general · gemini-2.0-flash

    locations and regional identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Brescia
    -0.64
     milano
    -0.63
     Majefty
    -0.62
     zaragoza
    -0.62
     oliveira
    -0.61
    =[]
    -0.61
     marseille
    -0.61
     Cæsar
    -0.60
     lyon
    -0.60
     Haarlem
    -0.60
    POSITIVE LOGITS
     overseas
    0.73
     someplace
    0.62
     South
    0.61
     abroad
    0.60
     Florida
    0.60
     south
    0.60
     southern
    0.58
     Texas
    0.58
    somewhere
    0.58
     Mexico
    0.58
    Act Density 0.307%

    No Known Activations