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

    Neuronpedia

    INDEX
    Explanations

    possession and following nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wa
    0.37
    ika
    0.35
     بين
    0.35
     l
    0.34
     보
    0.33
    ida
    0.33
     entre
    0.33
    ides
    0.33
    ists
    0.32
    sa
    0.32
    POSITIVE LOGITS
    ی
    0.32
    ာ
    0.30
    า
    0.30
    ി
    0.30
    RUPTION
    0.30
    י
    0.29
     contexte
    0.28
     twierd
    0.28
    Diversity
    0.28
    ੇ
    0.28
    Act Density 2.932%

    No Known Activations