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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.73
     TResult
    -0.72
    InputBorder
    -0.71
    )”.
    -0.70
     }}}{
    -0.69
    ),”
    -0.69
     SIMBAD
    -0.69
    !")
    -0.69
    runApp
    -0.69
     %>%
    -0.68
    POSITIVE LOGITS
    HtmlAttribute
    0.57
    principalTable
    0.50
     and
    0.43
     not
    0.39
     knowing
    0.38
     recognizing
    0.36
     timing
    0.35
     really
    0.34
     it
    0.34
    centerY
    0.33
    Act Density 0.003%

    No Known Activations