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

    Neuronpedia

    INDEX
    Explanations

    padding around elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    朽
    0.41
     caseload
    0.40
     transitory
    0.39
     abstracto
    0.39
     spinning
    0.38
     działalności
    0.38
    الإنجليزية
    0.38
     boilers
    0.38
    initializing
    0.38
    hovah
    0.37
    POSITIVE LOGITS
     padding
    1.47
    Padding
    1.38
     Padding
    1.34
    padding
    1.30
     margin
    1.19
     margins
    1.18
    Margin
    1.11
     Margin
    1.10
    Margins
    1.09
    margin
    1.08
    Act Density 0.018%

    No Known Activations