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

    Neuronpedia

    INDEX
    Explanations

    XML document structure elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मायणी
    0.47
    肐
    0.45
    讲
    0.40
    㖦
    0.40
    ⼦
    0.39
     Forgot
    0.39
    ADDING
    0.39
     ইংরাজ
    0.39
    ImageQueue
    0.39
    唪
    0.39
    POSITIVE LOGITS
     xml
    0.64
     xlink
    0.63
    xml
    0.61
     XML
    0.58
    XML
    0.55
     xmlns
    0.50
    jats
    0.49
    xlink
    0.46
     cor
    0.46
     Cor
    0.45
    Act Density 0.002%

    No Known Activations