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

    Neuronpedia

    INDEX
    Explanations

    street names and geographic locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mod
    0.59
     the
    0.55
     regex
    0.54
    0.54
     a
    0.54
     emotion
    0.53
     context
    0.52
     tuple
    0.52
     object
    0.52
     not
    0.52
    POSITIVE LOGITS
     Avenue
    1.04
     Blvd
    1.01
     Boulevard
    1.00
     Parkway
    0.99
     Township
    0.97
     Terrace
    0.97
     Creek
    0.97
     Plaza
    0.96
     Farms
    0.95
     Springs
    0.94
    Act Density 0.127%

    No Known Activations