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

    Neuronpedia

    INDEX
    Explanations

    Nazi Germany and World War II

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fracking
    0.81
     Drupal
    0.80
     Laravel
    0.76
     McIl
    0.76
     AED
    0.75
     backpacking
    0.75
     Cedar
    0.71
     tacos
    0.71
     Sierra
    0.69
     cedar
    0.68
    POSITIVE LOGITS
     Nazi
    2.33
     Hitler
    2.15
    Nazi
    1.88
     German
    1.80
     Axis
    1.80
     Germany
    1.76
     Nazis
    1.75
     fascist
    1.75
    German
    1.70
     हिटलर
    1.70
    Act Density 0.134%

    No Known Activations