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

    Neuronpedia

    INDEX
    Explanations

    dimensions and units like feet, seconds, len

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্ের
    1.02
    лна
    0.88
     ﺍﻟ
    0.88
    孀
    0.88
     głównie
    0.87
    ্া
    0.86
     ruim
    0.85
    㬶
    0.84
    䩕
    0.84
     urgente
    0.83
    POSITIVE LOGITS
    \
    0.84
    '
    0.74
    /
    0.72
    <start_of_image>
    0.71
    <
    0.66
    EN
    0.65
    stone
    0.65
    Y
    0.65
    apt
    0.64
    borderColor
    0.64
    Act Density 0.013%

    No Known Activations