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

    Neuronpedia

    INDEX
    Explanations

    Indian cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soluciones
    -0.85
     Retrieve
    -0.84
    EMBRE
    -0.83
     conceito
    -0.82
     wonderful
    -0.82
     Luego
    -0.79
    ┘
    -0.78
    ená
    -0.78
     człowie
    -0.77
     жест
    -0.77
    POSITIVE LOGITS
     city
    1.52
     region
    1.19
    ites
    1.02
     division
    1.00
    city
    0.98
     City
    0.97
     outskirts
    0.97
    有名
    0.95
     district
    0.93
     branch
    0.93
    Act Density 0.028%

    No Known Activations