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

    Neuronpedia

    INDEX
    Explanations

    outlines and section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused354>
    0.33
    ቺ
    0.32
    മ്ബ
    0.31
    だけでなく
    0.31
     করিয়াছিল
    0.31
    ಿತ
    0.31
    ଉ
    0.30
     demás
    0.30
    古い
    0.30
    ওই
    0.29
    POSITIVE LOGITS
     Explained
    0.66
     -
    0.65
    详解
    0.63
     Overview
    0.63
     –
    0.62
    </h2>
    0.59
    </h3>
    0.59
     overview
    0.57
    Overview
    0.54
     czyli
    0.53
    Act Density 0.207%

    No Known Activations