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

    Neuronpedia

    INDEX
    Explanations

    engaging the reader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Chrom
    0.38
     மனு
    0.37
    ҽ
    0.36
     الرجال
    0.36
     livré
    0.36
    使い
    0.35
     utilizzato
    0.35
     návr
    0.35
     kullanım
    0.34
     Künstler
    0.34
    POSITIVE LOGITS
     readers
    3.19
     reader
    3.05
    读者
    2.72
     Readers
    2.70
    readers
    2.59
    reader
    2.58
    Readers
    2.47
     Reader
    2.38
     чита
    2.36
     readership
    2.31
    Act Density 0.011%

    No Known Activations