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

    Neuronpedia

    INDEX
    Explanations

    words starting with De-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    吊
    0.41
    ført
    0.39
    螈
    0.38
    辅助
    0.38
     创建
    0.37
    VARIABLES
    0.36
     변화
    0.36
    地面
    0.36
    铖
    0.36
    iek
    0.36
    POSITIVE LOGITS
     Dek
    1.05
     De
    0.91
    Dek
    0.88
    De
    0.88
     Dec
    0.87
     dek
    0.83
     Decker
    0.81
    de
    0.81
     де
    0.79
    Dec
    0.77
    Act Density 0.079%

    No Known Activations