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

    Neuronpedia

    INDEX
    Explanations

    sentence endings followed by pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ত্রী
    0.74
    তিপ
    0.70
    های
    0.69
    তম
    0.67
    蚪
    0.66
    ভূতি
    0.66
    propylene
    0.65
    apeut
    0.65
    Мо
    0.64
    駐
    0.64
    POSITIVE LOGITS
    
    1.43
     Adds
    1.33
     And
    1.26
     ujarnya
    1.24
     Vocabulary
    1.21
     Tämä
    1.21
     That
    1.20
    这句话
    1.18
     Emotions
    1.18
     This
    1.18
    Act Density 0.326%

    No Known Activations