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

    Neuronpedia

    INDEX
    Explanations

    contact us, our

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    私は
    0.69
     करूंगा
    0.64
    хожу
    0.63
    ிறேன்
    0.59
    uyorum
    0.59
     છું
    0.57
     tengo
    0.55
    ıyorum
    0.55
     हूं
    0.55
     دارم
    0.55
    POSITIVE LOGITS
     আমাদের
    1.86
     our
    1.85
    我们的
    1.64
     ours
    1.61
     mūsų
    1.59
    আমাদের
    1.55
     हमारे
    1.53
     ہمارے
    1.53
    我們的
    1.52
     nuestros
    1.52
    Act Density 0.010%

    No Known Activations