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

    Neuronpedia

    INDEX
    Explanations

    revolution and revolutionary concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ку
    1.16
    نا
    1.13
    ра
    1.10
    ä
    1.05
    ما
    1.02
    ي
    0.95
    io
    0.95
    ના
    0.95
    یا
    0.94
     déplacer
    0.93
    POSITIVE LOGITS
     revolution
    1.08
     Revolution
    0.97
    Revolution
    0.89
    revolution
    0.89
     Revolutionary
    0.88
     револю
    0.82
     revolutionary
    0.79
     revolucion
    0.78
    }
    0.75
     revolutions
    0.70
    Act Density 0.021%

    No Known Activations