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

    Neuronpedia

    INDEX
    Explanations

    news headlines and business decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     VERY
    1.10
     extremamente
    1.08
     вашего
    1.07
     votre
    1.02
     YOUR
    1.02
    Whilst
    1.02
     jouw
    1.02
     вашей
    1.02
     estremamente
    1.01
     σας
    1.00
    POSITIVE LOGITS
     staffers
    1.25
     amid
    1.23
     lawmakers
    1.06
     tweaks
    1.04
     automakers
    1.02
     지난해
    1.02
     advisers
    1.01
     stints
    0.88
     tweaked
    0.87
     pricey
    0.86
    Act Density 0.029%

    No Known Activations