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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ($__
    -0.56
     ujednoznacz
    -0.54
     архивлан
    -0.54
    Datuak
    -0.53
     Lordships
    -0.52
     Italijanski
    -0.48
    честву
    -0.47
    minecraftforge
    -0.46
     دیگری
    -0.46
     the
    -0.46
    POSITIVE LOGITS
    verme
    0.54
    ArgsConstructor
    0.53
    esgue
    0.52
    ImageContext
    0.52
    ScopeManager
    0.52
    ParallelGroup
    0.50
    WebpackPlugin
    0.49
    WebControls
    0.49
    isci
    0.49
    glob
    0.49
    Act Density 0.002%

    No Known Activations