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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Portail
    -0.58
     <=",
    -0.57
    存于互联网档案馆
    -0.52
    TagMode
    -0.51
    AddTagHelper
    -0.50
    ंदीखरीदारी
    -0.50
     DIA
    -0.49
    LayoutStyle
    -0.49
    SourceChecksum
    -0.48
    Становништво
    -0.48
    POSITIVE LOGITS
    ']))
    0.52
     cí
    0.48
     second
    0.46
     Wikimedijinoj
    0.46
    antaranya
    0.46
    GHIJKLM
    0.45
     contextLoads
    0.45
    寸
    0.44
    ("")]
    0.44
     seco
    0.44
    Act Density 0.233%

    No Known Activations