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

    Neuronpedia

    INDEX
    Explanations

    Measure contains

    np_acts-logits-general · gemini-2.5-flash-lite

    https:// URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \
    0.41
     त
    0.27
    Т
    0.26
     française
    0.26
     Don
    0.26
     Brigham
    0.26
    Uart
    0.26
     Ireland
    0.26
     Frankreich
    0.25
     suche
    0.25
    POSITIVE LOGITS
    ों
    0.31
    ים
    0.28
    ો
    0.26
    য়ের
    0.25
    🔯
    0.24
     constat
    0.23
    го
    0.23
    í
    0.23
    '
    0.23
    <unused2182>
    0.22
    Act Density 10.448%

    No Known Activations