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

    Neuronpedia

    INDEX
    Explanations

    areas of activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Etc
    1.46
     etc
    1.46
     ইত্যাদি
    1.37
     тощо
    1.28
    etc
    1.22
     など
    1.20
     usw
    1.19
     आदि
    1.17
    など
    1.16
     इत्यादि
    1.14
    POSITIVE LOGITS
    ¹,
    0.72
    },-
    0.71
     \%,
    0.70
     thirteen
    0.67
    ైన
    0.65
    ٬
    0.64
    ,“
    0.63
    ”、“
    0.63
    ","$
    0.63
    Sea
    0.63
    Act Density 0.626%

    No Known Activations