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

    Neuronpedia

    INDEX
    Explanations

    locations and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     statunitense
    0.50
     strikeouts
    0.48
     outfitted
    0.47
     campgrounds
    0.47
     estadounidense
    0.47
    ޙ
    0.46
     américaine
    0.46
     Amerikan
    0.46
     Amerikaanse
    0.44
     poiché
    0.44
    POSITIVE LOGITS
     UK
    0.62
     Britain
    0.56
     centre
    0.53
     England
    0.49
     adverts
    0.49
    piry
    0.46
     postcode
    0.46
     supermarket
    0.46
     Tesco
    0.45
     colourful
    0.45
    Act Density 0.014%

    No Known Activations