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

    Neuronpedia

    INDEX
    Explanations

    street and city names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Newbury
    0.57
    sche
    0.49
    σιμοποι
    0.44
     Beyer
    0.41
     Islington
    0.40
    Sche
    0.40
    Brooklyn
    0.39
     Brooklyn
    0.39
     Fairfield
    0.39
    netlify
    0.39
    POSITIVE LOGITS
     CBD
    0.70
     Pitt
    0.61
    CBD
    0.59
     CBN
    0.54
    Pitt
    0.53
     Martin
    0.52
     martin
    0.52
     George
    0.51
    Martin
    0.50
    George
    0.49
    Act Density 0.002%

    No Known Activations