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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     they
    2.51
     we
    2.17
     she
    2.17
     они
    2.00
     he
    2.00
    they
    1.94
     она
    1.91
     вони
    1.78
     он
    1.63
     вона
    1.62
    POSITIVE LOGITS
     que
    0.96
     कि
    0.81
     کہ
    0.79
    That
    0.79
     যে
    0.73
     dass
    0.69
     Que
    0.69
     whom
    0.68
    Que
    0.67
     QUE
    0.67
    Act Density 0.073%

    No Known Activations