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

    Neuronpedia

    INDEX
    Explanations

    compile

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compile
    -1.05
     compiling
    -1.01
    Compiled
    -0.98
     compiled
    -0.95
    compile
    -0.94
    compiled
    -0.91
    Compile
    -0.86
     compiles
    -0.82
     Compiled
    -0.81
     Compile
    -0.80
    POSITIVE LOGITS
    agrid
    0.59
     iprot
    0.56
     Winthrop
    0.54
    AntiForgeryToken
    0.54
    ✨:
    0.50
     altar
    0.49
    控
    0.49
    astéro
    0.48
    Semoga
    0.48
     programmes
    0.48
    Act Density 0.013%

    No Known Activations