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

    Neuronpedia

    INDEX
    Explanations

    XML attributes and elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ஒத்து
    0.46
    解放
    0.43
     좌
    0.41
     கடு
    0.38
    跑
    0.38
     धन
    0.36
     συνεργ
    0.36
     파
    0.36
    éo
    0.35
     постоянно
    0.35
    POSITIVE LOGITS
    xsi
    0.72
     attributes
    0.70
    attributes
    0.62
     xlink
    0.61
    xlink
    0.59
     atribut
    0.59
     xsi
    0.57
     attrib
    0.56
    CDATA
    0.55
     xmlns
    0.55
    Act Density 0.005%

    No Known Activations