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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to a person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    0.51
    我們
    0.48
     forgery
    0.47
    我們要
    0.47
    我们就
    0.47
    ି
    0.45
     ஒன்றை
    0.45
    কিছু
    0.44
     আমরা
    0.44
    ோம்
    0.44
    POSITIVE LOGITS
     wrote
    0.49
     flew
    0.46
    ffes
    0.46
     texted
    0.45
     could
    0.44
     wore
    0.44
    mming
    0.44
     can
    0.44
    泂
    0.43
    czy
    0.43
    Act Density 0.000%

    No Known Activations