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

    Neuronpedia

    INDEX
    Explanations

    implementing and impacting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Electronics
    0.48
     కృషి
    0.46
     bein
    0.46
     ولكن
    0.46
     Constru
    0.45
    ඖ
    0.45
     書い
    0.44
    Paul
    0.44
    ينا
    0.44
     Ping
    0.44
    POSITIVE LOGITS
    t
    0.57
    a
    0.56
    ানার
    0.52
    ून
    0.51
    пере
    0.45
    ство
    0.44
    доб
    0.44
    া
    0.44
    м
    0.44
    начально
    0.43
    Act Density 0.003%

    No Known Activations