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

    Neuronpedia

    INDEX
    Explanations

    part of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وعلى
    2.06
    IM
    1.95
     TMA
    1.88
    Дата
    1.84
    UR
    1.82
    Karnataka
    1.78
     Merkezi
    1.76
    OL
    1.73
    犸
    1.71
    ../../
    1.70
    POSITIVE LOGITS
    ীদার
    2.63
    ن
    2.58
    ت
    2.44
    tól
    2.13
    ীদ
    2.08
    м
    2.08
    으로써
    2.03
     integrante
    2.03
    слежи
    2.02
    с
    1.99
    Act Density 0.045%

    No Known Activations