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

    Neuronpedia

    INDEX
    Explanations

    political awareness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ס
    0.56
    د
    0.50
    ד
    0.48
    많은
    0.46
    许多
    0.44
    نع
    0.44
    т
    0.44
    ים
    0.44
    س
    0.44
    ט
    0.43
    POSITIVE LOGITS
    OUIS
    0.50
     dulu
    0.48
     told
    0.47
     dahin
    0.47
     keeper
    0.47
     commissioner
    0.46
    ৭১
    0.45
     moeten
    0.45
     backbone
    0.42
     feas
    0.42
    Act Density 0.017%

    No Known Activations