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

    Neuronpedia

    INDEX
    Explanations

    qualified international students

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    轳
    0.40
     कैटेगरी
    0.39
    란
    0.39
     полную
    0.38
     любом
    0.37
    ﹂
    0.37
    षण
    0.37
    Situ
    0.37
     faulted
    0.36
     கண
    0.36
    POSITIVE LOGITS
    WK
    0.38
    pok
    0.37
    assem
    0.36
     potom
    0.36
     remarked
    0.36
    ーク
    0.36
    arashtra
    0.35
    THANK
    0.35
    ัส
    0.35
     Shak
    0.35
    Act Density 0.000%

    No Known Activations