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

    Neuronpedia

    INDEX
    Explanations

    food item descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    COVERY
    0.43
     Chartered
    0.40
    溟
    0.39
    örungen
    0.39
     ABO
    0.39
     પાસે
    0.39
     फाउंड
    0.38
    棻
    0.38
     ஆத
    0.38
     Sung
    0.38
    POSITIVE LOGITS
     stumble
    0.36
    특별
    0.36
     mph
    0.35
     temporary
    0.35
     특별
    0.35
    ණ්ඩ
    0.35
     chopsticks
    0.35
    이렇게
    0.35
    ակի
    0.35
     suburban
    0.34
    Act Density 0.001%

    No Known Activations