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

    Neuronpedia

    INDEX
    Explanations

    male or female roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ный
    0.99
     `<`,
    0.89
    িক্স
    0.83
    #[
    0.79
    ফর
    0.79
    ৩৪
    0.78
    તના
    0.77
     "\
    0.76
     "\""
    0.76
    iper
    0.76
    POSITIVE LOGITS
    volent
    1.98
    volence
    1.77
    folk
    1.61
     empowerment
    1.45
    娲
    1.33
     reproductive
    1.31
    媧
    1.29
    agerie
    1.26
     voices
    1.25
    friends
    1.24
    Act Density 0.096%

    No Known Activations