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

    Neuronpedia

    INDEX
    Explanations

    town, location descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अना
    0.44
    arino
    0.40
    چل
    0.38
     मच्छर
    0.38
    Generalized
    0.37
    Ẓ
    0.37
     کراچی
    0.36
     chh
    0.36
    మర్శ
    0.36
    宓
    0.36
    POSITIVE LOGITS
     town
    0.56
     towns
    0.54
     Towns
    0.52
     Town
    0.41
     TOWN
    0.41
     supermarkets
    0.40
     Denote
    0.40
    segu
    0.39
     войне
    0.38
     élèves
    0.38
    Act Density 0.014%

    No Known Activations