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

    Neuronpedia

    INDEX
    Explanations

    city name components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     molecule
    0.65
     actionable
    0.61
     altru
    0.57
     gen
    0.54
     tuple
    0.54
     pervasive
    0.54
     achievable
    0.54
     meta
    0.53
     be
    0.52
     object
    0.52
    POSITIVE LOGITS
     città
    1.11
    ópolis
    1.08
     Island
    1.06
     City
    1.06
     cidade
    1.05
     города
    1.03
    ville
    1.03
     város
    1.01
     เมือง
    1.00
    ersburg
    1.00
    Act Density 0.287%

    No Known Activations