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

    Neuronpedia

    INDEX
    Explanations

    Here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    যায়
    0.47
     सरोवर
    0.44
    流
    0.44
    чь
    0.44
     suivent
    0.44
    সহিত
    0.44
     सूर्
    0.42
     ভারতবর্ষে
    0.41
     retShape
    0.41
    沢山
    0.41
    POSITIVE LOGITS
     seconds
    0.47
    seconds
    0.46
    <strong>
    0.46
    $
    0.42
     $
    0.41
    ione
    0.41
    //
    0.41
     man
    0.40
    ibli
    0.39
    ia
    0.39
    Act Density 0.008%

    No Known Activations