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

    Neuronpedia

    INDEX
    Explanations

    CV, application, skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MLB
    0.57
    Verizon
    0.54
    MLB
    0.53
     américaine
    0.51
    credential
    0.51
    美國
    0.50
    Iowa
    0.50
    Colorado
    0.49
     Amtrak
    0.49
    Seattle
    0.48
    POSITIVE LOGITS
     postcode
    0.66
     lorry
    0.65
     adverts
    0.63
     Wigan
    0.56
     advert
    0.55
     soya
    0.54
     Swindon
    0.54
     summarised
    0.53
     Bournemouth
    0.53
     summarise
    0.52
    Act Density 0.003%

    No Known Activations