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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns like their

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obtuvo
    0.49
    punyai
    0.44
    ន្ថ
    0.42
    鞭
    0.42
     विशेषज्ञ
    0.41
     DispatchQueue
    0.40
    તિ
    0.39
     avoir
    0.38
     ayant
    0.38
     chuyên
    0.38
    POSITIVE LOGITS
     Their
    0.42
    Their
    0.41
     THEIR
    0.40
    INTER
    0.39
    ここでは
    0.39
    介
    0.38
     INTER
    0.38
     their
    0.37
    CY
    0.37
     юни
    0.36
    Act Density 0.000%

    No Known Activations