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

    Neuronpedia

    INDEX
    Explanations

    Empire and colonial rule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    માં
    0.46
    <unused497>
    0.45
    <unused1068>
    0.45
    <unused641>
    0.44
    даги
    0.43
    <unused2017>
    0.43
    <unused1136>
    0.43
    పై
    0.42
    <unused561>
    0.42
    ך
    0.42
    POSITIVE LOGITS
     \
    0.44
    }
    0.37
    {
    0.35
     auctions
    0.32
     Empire
    0.31
     crosses
    0.31
     Aquatic
    0.31
    رام
    0.31
     empire
    0.30
     crushes
    0.30
    Act Density 0.032%

    No Known Activations