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

    Neuronpedia

    INDEX
    Explanations

    two third

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     জনাব
    0.82
     মাননীয়
    0.77
     Whilst
    0.74
     యొక్క
    0.72
    Whilst
    0.72
     উক্ত
    0.68
     గారి
    0.68
     whilst
    0.68
    ళ్ళు
    0.63
     করবার
    0.63
    POSITIVE LOGITS
     छह
    0.64
     지난해
    0.64
     sejumlah
    0.63
     लिहाजा
    0.60
     मसलन
    0.60
     உள்ளிட்ட
    0.59
     yüzde
    0.57
     कवाय
    0.57
     earmarked
    0.57
     ഏറെ
    0.56
    Act Density 0.001%

    No Known Activations