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

    Neuronpedia

    INDEX
    Explanations

    west followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Haar
    0.44
    大的
    0.41
    edere
    0.40
    ه
    0.39
    েক্টর
    0.39
    ethylene
    0.39
     স্থান
    0.39
     معامل
    0.38
     Stewardship
    0.38
    orske
    0.38
    POSITIVE LOGITS
    West
    0.80
     West
    0.76
     西
    0.75
     पश्चिम
    0.74
     westward
    0.72
    west
    0.72
     WEST
    0.72
     Westen
    0.71
     western
    0.70
    西
    0.70
    Act Density 0.010%

    No Known Activations