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

    Neuronpedia

    INDEX
    Explanations

    structured lists and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olverine
    0.46
     ربعه
    0.43
    nikom
    0.42
    ಾವ್
    0.39
    muted
    0.38
    ĺ
    0.38
    licted
    0.37
     위한
    0.37
    icc
    0.36
    认为是
    0.36
    POSITIVE LOGITS
    Detailed
    0.39
    チック
    0.38
     detailed
    0.38
     상세
    0.37
    天氣
    0.37
     utilice
    0.36
    住宅
    0.36
     естественно
    0.35
    利用
    0.35
     naturl
    0.35
    Act Density 0.001%

    No Known Activations