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

    Neuronpedia

    INDEX
    Explanations

    shops and products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neighborhoods
    0.58
     bicyclists
    0.57
     sidewalks
    0.57
     worrisome
    0.57
     counselors
    0.56
     grayish
    0.56
     meager
    0.55
     cognizant
    0.55
     geologic
    0.54
     armored
    0.54
    POSITIVE LOGITS
     £
    1.28
     UK
    1.21
     (£
    1.16
     postcode
    1.13
     bespoke
    1.12
     favourites
    1.04
     Colour
    0.99
     colourful
    0.96
    £
    0.96
     personalised
    0.96
    Act Density 0.012%

    No Known Activations