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

    Neuronpedia

    INDEX
    Explanations

    formal and official contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     플러스
    0.47
    走进
    0.47
    营养
    0.46
     கட்டமை
    0.45
    独特的
    0.45
    神经
    0.45
    类似于
    0.44
    常见的
    0.44
    回归
    0.44
    组件
    0.43
    POSITIVE LOGITS
     telegram
    0.59
     annexed
    0.53
     Secretary
    0.52
     Messrs
    0.52
     endeavoured
    0.51
     remarked
    0.50
     earnestly
    0.50
     forwarded
    0.50
    意見
    0.50
     remon
    0.50
    Act Density 0.007%

    No Known Activations