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

    Neuronpedia

    INDEX
    Explanations

    beauty, morality, animal behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    บ
    0.50
    דיה
    0.48
    演員
    0.47
    典
    0.47
     Joshi
    0.46
    歌手
    0.46
     Amiri
    0.45
     Josie
    0.45
    百年
    0.45
     CENT
    0.45
    POSITIVE LOGITS
    ied
    0.50
    liced
    0.50
    ial
    0.48
    aap
    0.46
    iala
    0.46
    ales
    0.46
    nullptr
    0.45
    ayang
    0.45
     behaviors
    0.45
    aling
    0.44
    Act Density 0.002%

    No Known Activations