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

    Neuronpedia

    INDEX
    Explanations

    currency, profit, exchange, values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     speedy
    0.25
    addr
    0.23
     disabilities
    0.23
    waitUntil
    0.22
     hostess
    0.22
    ल्पनिक
    0.22
    িমূলক
    0.22
    ார
    0.22
    oinen
    0.21
    ttl
    0.21
    POSITIVE LOGITS
    ست
    0.28
    ר
    0.28
    وہ
    0.25
     الدراسي
    0.24
     η
    0.23
    GameObject
    0.23
     уро
    0.23
    مش
    0.22
    ःख
    0.22
    ب
    0.22
    Act Density 0.382%

    No Known Activations