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

    Neuronpedia

    INDEX
    Explanations

    tech and acronyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.64
    ARP
    -0.56
    esgue
    -0.48
     transfieras
    -0.47
     CURIAM
    -0.47
    lge
    -0.46
    uxley
    -0.46
     eventdata
    -0.45
    ixante
    -0.45
    atott
    -0.45
    POSITIVE LOGITS
    脚注の使い方
    0.58
     Bulletin
    0.57
    onViewCreated
    0.54
     bulletin
    0.54
     muualla
    0.53
     onBind
    0.53
    rungsseite
    0.50
     Nah
    0.49
    \|_{\
    0.47
    initComponents
    0.47
    Act Density 0.005%

    No Known Activations