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

    Neuronpedia

    INDEX
    Explanations

    the word "preserve"

    oai_token-act-pair · gemini-2.0-flash

    preserve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     متعلقه
    -1.02
    LinkId
    -1.00
    <bos>
    -0.98
     beginnetje
    -0.97
    InjectAttribute
    -0.94
    ChildScrollView
    -0.93
     InputDecoration
    -0.92
    afficheront
    -0.88
     pinulongan
    -0.85
    JspWriter
    -0.85
    POSITIVE LOGITS
     all
    0.59
    ьте
    0.56
     what
    0.48
     cuantas
    0.48
     Pathways
    0.48
    for
    0.48
     at
    0.48
    en
    0.47
    いかない
    0.47
    essex
    0.46
    Act Density 1.413%

    No Known Activations