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

    Neuronpedia

    INDEX
    Explanations

    our actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আমাকে
    0.81
    告诉我
    0.74
    让我
    0.73
     मुझसे
    0.73
    給我
    0.69
    讓我
    0.69
     తాను
    0.69
     mnie
    0.68
     मुझ
    0.68
     मुझे
    0.64
    POSITIVE LOGITS
     ourselves
    2.95
     our
    1.73
     আমাদের
    1.68
     nossos
    1.68
    我们的
    1.66
     nossas
    1.64
     nuestros
    1.63
    我們的
    1.63
     naše
    1.62
     наших
    1.58
    Act Density 0.022%

    No Known Activations