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

    Neuronpedia

    INDEX
    Explanations

    measurement or quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ().
    0.24
     convolutional
    0.24
    (),
    0.23
     {
    0.23
    文字列
    0.23
     regex
    0.22
     />
    0.22
     +=
    0.21
     whose
    0.21
                    
    0.21
    POSITIVE LOGITS
    Dried
    0.22
     dike
    0.21
    饮食
    0.21
     옷
    0.21
    Waters
    0.20
    饴
    0.20
    흡
    0.20
     earthen
    0.20
    Dry
    0.19
     tắm
    0.19
    Act Density 0.001%

    No Known Activations