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

    Neuronpedia

    INDEX
    Explanations

    scientific and engineering innovation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ગી
    0.42
    inosaur
    0.40
     পালন
    0.37
     ఎదు
    0.36
    adaş
    0.35
     Bollinger
    0.35
     Liebig
    0.34
    劊
    0.34
     refused
    0.33
     및
    0.33
    POSITIVE LOGITS
     dương
    0.41
    ား
    0.36
    blogs
    0.34
    หล
    0.33
    ::-
    0.33
    ͗
    0.33
    著作
    0.32
    钝
    0.32
    తో
    0.31
     främ
    0.31
    Act Density 0.016%

    No Known Activations