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

    Neuronpedia

    INDEX
    Explanations

    namely, that is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.39
    \
    0.33
    \...
    0.32
    "
    0.32
     -
    0.31
    ...'
    0.31
    ...
    0.30
    ",
    0.30
    '।
    0.30
    gleichen
    0.30
    POSITIVE LOGITS
     namely
    0.57
     тобто
    0.54
     yakni
    0.52
    namely
    0.50
    つまり
    0.47
    也就是说
    0.46
    也就是
    0.43
     ovvero
    0.41
     यानी
    0.41
     அதாவது
    0.41
    Act Density 0.181%

    No Known Activations