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

    Neuronpedia

    INDEX
    Explanations

    CodeIgniter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ቮ
    0.46
     یورپی
    0.46
    rène
    0.43
    Finn
    0.42
    羧
    0.42
    ⛧
    0.42
    OrderFlight
    0.41
     hémorro
    0.41
    curité
    0.41
    QueueMutex
    0.41
    POSITIVE LOGITS
     Malaysia
    1.38
     Malaysian
    1.29
     malaysia
    1.23
    Malaysia
    1.19
     मलेशिया
    1.11
     Malays
    1.09
     Kuala
    1.05
     Sdn
    0.95
     Johor
    0.95
     Selangor
    0.95
    Act Density 0.001%

    No Known Activations