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

    Neuronpedia

    INDEX
    Explanations

    particularly + modifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    们
    1.84
    it
    1.75
    ing
    1.71
    る
    1.70
    ت
    1.57
    il
    1.55
    가
    1.55
    م
    1.54
    ই
    1.54
    υτό
    1.52
    POSITIVE LOGITS
    s
    1.87
     dotycz
    1.55
    ्स
    1.52
    sax
    1.44
     adanya
    1.43
    sellers
    1.39
    sas
    1.38
    utation
    1.36
    sda
    1.34
     Lint
    1.32
    Act Density 0.341%

    No Known Activations