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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arnold
    -2.19
    Arnold
    -1.95
     ARNOLD
    -1.63
     arn
    -0.93
     vientos
    -0.52
     Schwarzenegger
    -0.51
     noastră
    -0.51
    ⛈
    -0.50
     múltiple
    -0.50
     stället
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.73
    BeginInit
    0.61
     esternos
    0.60
    Jeografia
    0.60
     EconPapers
    0.57
    IsContent
    0.57
    awtextra
    0.56
    ilige
    0.55
     препратки
    0.54
    SuspendLayout
    0.54
    Act Density 0.012%

    No Known Activations