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

    Neuronpedia

    INDEX
    Explanations

    possessive pronoun related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دارید
    0.89
     তাঁরা
    0.88
     是
    0.87
     içeren
    0.85
     którzy
    0.85
    添加到
    0.84
    都是
    0.84
     تھیں
    0.82
    有助于
    0.82
    которы
    0.82
    POSITIVE LOGITS
     itself
    1.93
     its
    1.79
     Its
    1.49
    its
    1.42
    它的
    1.38
    Its
    1.38
     ತನ್ನ
    1.24
     자체
    1.09
     അതിന്റെ
    1.04
    因为它
    1.01
    Act Density 0.239%

    No Known Activations