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

    Neuronpedia

    INDEX
    Explanations

    socializing and gender roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stari
    0.49
    Input
    0.45
    Обра
    0.45
    在庫
    0.45
    Data
    0.44
     podataka
    0.43
     विशाल
    0.41
     vivienda
    0.41
    Currency
    0.41
    renzia
    0.40
    POSITIVE LOGITS
     乾燥
    0.51
     ช่วย
    0.49
     lendemain
    0.49
     PAR
    0.48
     pH
    0.48
     dissolves
    0.48
     উপযোগী
    0.47
    乳
    0.47
    感じで
    0.47
     分
    0.46
    Act Density 0.000%

    No Known Activations