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

    Neuronpedia

    INDEX
    Explanations

    post-war historical events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ahmed
    0.78
    lectic
    0.77
     Pharaoh
    0.72
    墨
    0.71
     Laravel
    0.69
     Alexis
    0.69
     охра
    0.68
     Maroon
    0.68
     Eth
    0.67
     oasis
    0.67
    POSITIVE LOGITS
     postwar
    1.12
    重建
    1.05
     liberated
    1.02
     post
    1.02
    Post
    1.01
     pós
    0.99
     NATO
    0.95
    German
    0.94
     Nato
    0.94
     vanqu
    0.94
    Act Density 0.107%

    No Known Activations