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

    Neuronpedia

    INDEX
    Explanations

    stereotypes and prejudice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     according
    0.41
    Youth
    0.41
     Youth
    0.40
    yı
    0.40
    ンプル
    0.39
    蹿
    0.39
    Sat
    0.38
     Histories
    0.37
     beaches
    0.37
     다양
    0.37
    POSITIVE LOGITS
     découvert
    0.47
     croire
    0.44
     découvrir
    0.43
     visiting
    0.42
     visitare
    0.42
     belladone
    0.42
     hvis
    0.41
     choix
    0.40
    setRoi
    0.39
     répar
    0.39
    Act Density 0.000%

    No Known Activations