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

    Neuronpedia

    INDEX
    Explanations

    list items with bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     এসেছে
    0.38
     ভেদ
    0.38
     रिस
    0.38
     ресурс
    0.38
     भेद
    0.36
    มีการ
    0.36
    となり
    0.36
     दर्शा
    0.35
    entered
    0.35
    Entered
    0.35
    POSITIVE LOGITS
     études
    0.40
     पोर्न
    0.40
    ča
    0.39
    <0x9A>
    0.39
    ](../
    0.38
    ჯგუფი
    0.37
     ezért
    0.37
     Boiling
    0.36
    ტი
    0.36
    િજા
    0.36
    Act Density 0.000%

    No Known Activations