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

    Neuronpedia

    INDEX
    Explanations

    proper names and their endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ഒഴിവാ
    0.19
     عوامل
    0.18
     Wissen
    0.18
     Aprove
    0.18
    您
    0.18
     لكل
    0.18
     Neste
    0.18
     Usted
    0.17
     Что
    0.17
     Plugging
    0.17
    POSITIVE LOGITS
    had
    0.22
    é
    0.21
    ak
    0.20
    á
    0.20
    ar
    0.18
    am
    0.17
    éz
    0.17
    ul
    0.17
     women
    0.17
    ína
    0.17
    Act Density 0.508%

    No Known Activations