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

    Neuronpedia

    INDEX
    Explanations

    quoted text starts or dialogue markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আমি
    0.54
     உங்கள்
    0.52
    Your
    0.49
     your
    0.48
    You
    0.47
     אני
    0.47
    １
    0.46
     நான்
    0.46
    1
    0.46
     You
    0.44
    POSITIVE LOGITS
     "'
    0.84
     pihaknya
    0.78
     “‘
    0.77
     "...
    0.70
     "****
    0.68
     “…
    0.67
     "`
    0.66
     "***
    0.59
     "¿
    0.59
     "[
    0.58
    Act Density 0.015%

    No Known Activations