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

    Neuronpedia

    INDEX
    Explanations

    our shared understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    私は
    1.58
     me
    1.38
     எனக்கு
    1.35
     my
    1.33
    我会
    1.29
     мне
    1.27
    me
    1.26
    私が
    1.24
    私も
    1.21
     बताऊंगा
    1.20
    POSITIVE LOGITS
     ourselves
    3.29
     نحن
    2.77
     наших
    2.52
     знаем
    2.49
     можем
    2.44
     nossos
    2.42
     unseren
    2.41
     nuestras
    2.40
     nossas
    2.40
     нашим
    2.40
    Act Density 0.057%

    No Known Activations