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

    Neuronpedia

    INDEX
    Explanations

    social development and science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    odigd
    0.47
    紵
    0.44
    姍
    0.43
    ጨም
    0.42
    撾
    0.42
    銈
    0.42
     በጣም
    0.42
    嗶
    0.41
     ምልክ
    0.41
    蛲
    0.40
    POSITIVE LOGITS
    社会
    0.62
    美好的
    0.55
    美好
    0.53
    自我
    0.53
     connot
    0.52
     connotation
    0.52
    发展
    0.52
    精神
    0.49
    理性
    0.49
     social
    0.49
    Act Density 0.023%

    No Known Activations