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

    Neuronpedia

    INDEX
    Explanations

    Introduction to concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ๑
    0.33
    டெ
    0.32
    Begin
    0.29
    Gravity
    0.29
    Shape
    0.29
    Flex
    0.29
    Regular
    0.28
    Vers
    0.28
     ஒ
    0.28
    Complex
    0.28
    POSITIVE LOGITS
    <unused2020>
    0.36
    <unused421>
    0.36
    <unused455>
    0.35
    <unused235>
    0.35
    <unused467>
    0.35
    <unused495>
    0.35
     зокрема
    0.35
    <unused532>
    0.35
    <unused626>
    0.35
    <unused550>
    0.34
    Act Density 0.007%

    No Known Activations