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

    Neuronpedia

    INDEX
    Explanations

    probing questions based on answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.50
    Osm
    0.47
    桀
    0.41
     بنیادی
    0.39
     تعرض
    0.38
     యొక్క
    0.38
     Osm
    0.37
    众多
    0.37
     emails
    0.37
    www
    0.37
    POSITIVE LOGITS
     लकार
    0.50
    䤃
    0.49
     arreg
    0.48
    पति
    0.45
    ਪ
    0.44
     nazionali
    0.43
    logne
    0.43
    ̰
    0.43
    ណ៌
    0.43
     probe
    0.43
    Act Density 0.000%

    No Known Activations