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

    Neuronpedia

    INDEX
    Explanations

    the word "the" and words related to applying things.

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.69
    ReusableCell
    -0.68
    RectangleBorder
    -0.68
    setVerticalGroup
    -0.65
    HasForeignKey
    -0.65
    Bioaccumulative
    -0.64
    ColumnHeaders
    -0.64
    onedDateTime
    -0.62
    ExecuteReader
    -0.62
     nationales
    -0.62
    POSITIVE LOGITS
    ########.
    0.65
     a
    0.52
     method
    0.50
     own
    0.49
     options
    0.49
     New
    0.48
    ัพท์
    0.48
    jestel
    0.48
     model
    0.47
    New
    0.47
    Act Density 0.700%

    No Known Activations