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

    Neuronpedia

    INDEX
    Explanations

    cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    loid
    0.76
    চ্ছ
    0.74
    oun
    0.73
    group
    0.73
    section
    0.72
    subsection
    0.71
    object
    0.70
    chrom
    0.70
    ostrum
    0.68
    input
    0.67
    POSITIVE LOGITS
     London
    3.20
     Seattle
    2.93
    London
    2.91
     Chicago
    2.90
     Tokyo
    2.87
     Londres
    2.81
     Toronto
    2.80
     Atlanta
    2.77
     Mumbai
    2.76
     Madrid
    2.74
    Act Density 0.514%

    No Known Activations