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

    Neuronpedia

    INDEX
    Explanations

    crowdedness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     traffic
    -1.43
     Traffic
    -1.31
    traffic
    -1.28
     congested
    -1.18
    Traffic
    -1.16
     congestion
    -1.13
     TRAFFIC
    -1.07
     tráfico
    -1.05
     overcrowded
    -1.00
     trafic
    -0.98
    POSITIVE LOGITS
    s
    0.75
    e
    0.66
    t
    0.66
    i
    0.59
    a
    0.56
    d
    0.54
    n
    0.49
    ity
    0.49
    o
    0.49
    g
    0.49
    Act Density 0.161%

    No Known Activations