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

    Neuronpedia

    INDEX
    Explanations

    defensive military positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.69
    x
    0.67
    ның
    0.64
    d
    0.63
    .(
    0.61
    (),
    0.60
    actin
    0.60
    z
    0.60
    ("
    0.59
    vai
    0.59
    POSITIVE LOGITS
     armies
    0.77
     rests
    0.71
     trenches
    0.69
     battlefield
    0.69
     troops
    0.68
     outpost
    0.68
     artillery
    0.66
     ridges
    0.65
    0.65
     implements
    0.64
    Act Density 0.027%

    No Known Activations