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

    Neuronpedia

    INDEX
    Explanations

    drinking vessels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     convolution
    0.43
    绡
    0.42
    convolution
    0.41
    kbeta
    0.40
    捆
    0.40
     Convolution
    0.39
    罾
    0.39
    Convolution
    0.39
     FTP
    0.39
     кло
    0.38
    POSITIVE LOGITS
     cups
    2.59
     cup
    2.55
     Cups
    2.20
    杯
    2.16
     mugs
    2.11
    cups
    2.11
    Cups
    2.11
    컵
    2.08
    cup
    1.91
     Cup
    1.88
    Act Density 0.079%

    No Known Activations