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

    Neuronpedia

    INDEX
    Explanations

    serial.begin setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বৈঠক
    0.45
     मीटिंग
    0.41
     squeezed
    0.39
    祂
    0.39
     meetings
    0.38
     মিটিং
    0.38
     squeeze
    0.37
    queeze
    0.36
    meetings
    0.36
    籬
    0.36
    POSITIVE LOGITS
    Serial
    1.05
     serial
    0.98
     Serial
    0.97
    serial
    0.95
     Serializable
    0.78
    Serializable
    0.76
     SERIAL
    0.73
     Serialization
    0.71
    SERIAL
    0.68
     serialization
    0.66
    Act Density 0.002%

    No Known Activations