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

    Neuronpedia

    INDEX
    Explanations

    Italian abstract nouns and Sapienza

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxe
    0.41
    یره
    0.39
     employed
    0.39
    اع
    0.38
    历
    0.38
    Our
    0.37
    സ്‌
    0.36
    াসী
    0.36
     ASF
    0.36
     Our
    0.36
    POSITIVE LOGITS
    ità
    0.73
    tà
    0.61
     degli
    0.57
    Sap
    0.57
    Università
    0.57
    à
    0.55
     sap
    0.54
     Sap
    0.54
    À
    0.48
    ilità
    0.48
    Act Density 0.006%

    No Known Activations