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

    Neuronpedia

    INDEX
    Explanations

    system paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    คัญ
    0.42
    λλα
    0.41
    뭔
    0.40
    чного
    0.40
    也很
    0.40
    верса
    0.40
    Markdown
    0.40
    隐含
    0.39
    жными
    0.39
    含义
    0.39
    POSITIVE LOGITS
     Zhang
    0.44
     Requires
    0.44
     Le
    0.41
     (!)
    0.41
     पत्नी
    0.41
     https
    0.41
     his
    0.40
     Muitos
    0.40
     (($
    0.39
     جميع
    0.39
    Act Density 0.063%

    No Known Activations