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

    Neuronpedia

    INDEX
    Explanations

    tell me or give me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    2.55
    You
    2.33
    you
    2.28
     You
    2.24
     vous
    2.06
     YOU
    1.99
     você
    1.98
    YOU
    1.96
     bạn
    1.94
     شما
    1.92
    POSITIVE LOGITS
     comigo
    0.90
     me
    0.87
     எங்களுக்கு
    0.78
    me
    0.76
     conmigo
    0.76
     Me
    0.74
     us
    0.73
     моём
    0.73
     لنا
    0.72
     меня
    0.71
    Act Density 0.105%

    No Known Activations