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

    Neuronpedia

    INDEX
    Explanations

    contrasting points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .|
    0.40
    .。
    0.38
    .
    0.38
    '
    0.37
     면
    0.35
    .•
    0.35
    ’
    0.34
     disrupts
    0.34
    *
    0.34
    \*
    0.34
    POSITIVE LOGITS
    少的
    0.34
    দিষ্ট
    0.33
     ترلاسه
    0.32
    dart
    0.32
    ianSpace
    0.32
    щего
    0.31
    天的
    0.31
    abspath
    0.31
     عرصے
    0.31
    깬
    0.31
    Act Density 7.942%

    No Known Activations