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

    Neuronpedia

    INDEX
    Explanations

    special characters and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    я
    1.43
    ണ്ടി
    1.33
    "
    1.25
     گرفتن
    1.24
    ദ്ധതി
    1.23
    Tuy
    1.22
    kannya
    1.21
    writeFile
    1.20
     việc
    1.20
     util
    1.19
    POSITIVE LOGITS
    ل
    1.79
    d
    1.69
    一个
    1.51
    ся
    1.51
    ский
    1.49
    ৭
    1.46
     customary
    1.42
    ق
    1.37
    lly
    1.35
    कार्यक्रम
    1.34
    Act Density 1.186%

    No Known Activations