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

    Neuronpedia

    INDEX
    Explanations

    declaration of queues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вересня
    0.49
     થયો
    0.43
     डिफर
    0.41
     вклю
    0.41
     ખા
    0.40
     tập
    0.39
     delve
    0.39
     onset
    0.39
     deepest
    0.38
    न्छ
    0.38
    POSITIVE LOGITS
    proposition
    0.53
    Kota
    0.51
    CAPTURE
    0.50
    K
    0.50
    Chennai
    0.49
    Fog
    0.48
    Customers
    0.47
    Messenger
    0.47
     constru
    0.46
    Mou
    0.46
    Act Density 0.000%

    No Known Activations