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

    Neuronpedia

    INDEX
    Explanations

    gender in demographics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </b>
    0.60
    y
    0.55
     "
    0.50
    </u>
    0.49
    ure
    0.49
    </i>
    0.48
     .
    0.46
     वर्मा
    0.46
    </strong>
    0.45
     Differences
    0.44
    POSITIVE LOGITS
     jähr
    0.61
    كثر
    0.58
    pleClass
    0.58
     enigmatic
    0.54
    हाल
    0.52
    ঙালি
    0.51
     ehemal
    0.50
    Gender
    0.50
     സഞ്ച
    0.50
    შ
    0.49
    Act Density 0.003%

    No Known Activations