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

    Neuronpedia

    INDEX
    Explanations

    gender and birth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verkehr
    0.46
    executive
    0.46
    soci
    0.46
    rice
    0.45
    ังหวัด
    0.44
    re
    0.44
    am
    0.44
    awati
    0.44
    swald
    0.42
    thal
    0.42
    POSITIVE LOGITS
     Caption
    0.55
     cụ
    0.49
    多
    0.48
     υψη
    0.46
    ர்கள்
    0.46
    并不
    0.46
    滴
    0.45
     Stories
    0.44
    の一部
    0.44
    の
    0.44
    Act Density 0.000%

    No Known Activations