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

    Neuronpedia

    INDEX
    Explanations

    function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    รู้จัก
    0.41
     भाषाओं
    0.40
    場合に
    0.40
     pertaining
    0.39
     تكعيب
    0.39
    wort
    0.39
    டும்ப
    0.39
    picture
    0.38
    த்தகைய
    0.38
     안내
    0.38
    POSITIVE LOGITS
     Canada
    0.38
     बांटा
    0.38
    ξει
    0.38
    Canada
    0.37
     divide
    0.36
     [
    0.36
     Sierra
    0.36
    ά
    0.35
     Now
    0.35
     pros
    0.35
    Act Density 0.004%

    No Known Activations