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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ၇
    0.25
    固体
    0.24
    ក្រោម
    0.24
    <unused1096>
    0.24
    smallskip
    0.23
     Kirkland
    0.23
    ÍC
    0.23
    湳
    0.22
    ˒
    0.22
    Eppo
    0.22
    POSITIVE LOGITS
     =
    0.28
    _
    0.28
     This
    0.28
    '
    0.28
     __
    0.27
     It
    0.25
     //
    0.25
     /*
    0.25
     &&
    0.25
    ))
    0.25
    Act Density 0.165%

    No Known Activations