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

    Neuronpedia

    INDEX
    Explanations

    `https`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bioavailability
    0.26
    ्यर्थ
    0.25
    ंगन
    0.25
    িল্প
    0.25
     proteínas
    0.25
    代谢
    0.25
    溶
    0.25
    溶液
    0.24
    䖝
    0.24
     pliers
    0.24
    POSITIVE LOGITS
    2
    0.37
    8
    0.36
    4
    0.35
    7
    0.34
    3
    0.32
    6
    0.32
    5
    0.31
    9
    0.31
    1
    0.30
    <unused100>
    0.29
    Act Density 0.031%

    No Known Activations