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

    Neuronpedia

    INDEX
    Explanations

    structured elements typical in academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Los Alamos preprint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.49
     känd
    -0.38
    ########.
    -0.35
     QtCore
    -0.34
    flats
    -0.34
    점
    -0.34
     reach
    -0.33
     nồi
    -0.33
    penup
    -0.33
    QtCore
    -0.33
    POSITIVE LOGITS
    HtmlAttribute
    0.60
    FormTagHelper
    0.53
    цезда
    0.51
    tagext
    0.50
    findpost
    0.49
    numerusform
    0.49
    sidemargin
    0.48
     BoxFit
    0.47
    VersionUID
    0.47
    visi
    0.47
    Act Density 0.029%

    No Known Activations