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

    Neuronpedia

    INDEX
    Explanations

    modelversion numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.48
    ok
    0.48
    1
    0.48
     milliseconds
    0.47
    %
    0.46
    od
    0.46
    ad
    0.43
     in
    0.43
     seconds
    0.42
     connectors
    0.42
    POSITIVE LOGITS
    MDEw
    0.41
     เขา
    0.40
    StarGo
    0.38
     جان
    0.37
    ряду
    0.36
    রাষ্ট
    0.35
    ورسٹی
    0.35
     sendiri
    0.35
    さま
    0.35
    ivät
    0.35
    Act Density 0.065%

    No Known Activations