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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    让自己
    0.52
     ด่า
    0.51
     자신이
    0.50
     પોતાની
    0.49
     அளவிற்கு
    0.48
     playfully
    0.48
    ตน
    0.46
    恐惧
    0.45
     வெறு
    0.44
     தனது
    0.43
    POSITIVE LOGITS
     our
    1.01
     আমাদের
    0.98
     ہمارے
    0.89
     your
    0.87
    আমাদের
    0.85
     нашей
    0.84
     nossa
    0.81
     naszej
    0.80
    我们的
    0.78
     हमारे
    0.77
    Act Density 0.001%

    No Known Activations