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

    Neuronpedia

    INDEX
    Explanations

    living organisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحياة
    0.57
     élet
    0.57
    Life
    0.55
     Life
    0.53
     život
    0.52
    生命
    0.50
     LIFE
    0.48
     life
    0.48
     जीवन
    0.47
     жизнью
    0.45
    POSITIVE LOGITS
     things
    0.55
     چیز
    0.53
    Things
    0.52
     Things
    0.50
    things
    0.49
    的东西
    0.49
     thing
    0.48
     चीजें
    0.48
    Thing
    0.48
    东西
    0.46
    Act Density 0.001%

    No Known Activations