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

    Neuronpedia

    INDEX
    Explanations

    first name followed by last name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PT
    0.47
    8
    0.45
    3
    0.43
    City
    0.42
    Citizens
    0.41
    4
    0.41
    ys
    0.39
    iki
    0.39
    UM
    0.39
    ama
    0.39
    POSITIVE LOGITS
    ாய்ச்சி
    0.40
    ॉफ्ट
    0.40
     当然
    0.39
     ficar
    0.39
     ovviamente
    0.39
     admittedly
    0.37
    桝
    0.37
    जुर्ग
    0.37
    翀
    0.37
    自分で
    0.37
    Act Density 0.001%

    No Known Activations