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

    Neuronpedia

    INDEX
    Explanations

    app titles or labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ண்டை
    0.43
     হবেন
    0.42
    )";
    0.42
    )}/>
    0.42
    ziert
    0.42
    ):
    0.41
    ূতন
    0.41
    餃
    0.40
    ᆺ
    0.40
    ponenten
    0.39
    POSITIVE LOGITS
     که
    0.57
    یل
    0.45
     that
    0.43
     महसूस
    0.43
     teks
    0.43
     nė
    0.43
     feel
    0.42
     کا
    0.42
     birthplace
    0.42
    که
    0.41
    Act Density 0.001%

    No Known Activations