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

    Neuronpedia

    INDEX
    Explanations

    Chinese abstract words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ନ୍
    0.79
     అని
    0.74
    subsection
    0.73
     nomor
    0.73
    inscription
    0.72
     membuat
    0.70
     susah
    0.70
    awarkan
    0.70
    enderung
    0.70
     sementara
    0.69
    POSITIVE LOGITS
    某
    0.82
    중
    0.74
    状态
    0.72
    当前
    0.71
    父
    0.71
    所有
    0.71
    贸易
    0.70
    某个
    0.70
    其中
    0.70
    生成
    0.70
    Act Density 0.020%

    No Known Activations